yaicli

Name	yaicli JSON
Version	0.8.10 JSON
	download
home_page	None
Summary	A simple CLI tool to interact with LLM
upload_time	2025-07-24 05:37:04
maintainer	None
docs_url	None
author	None
requires_python	>=3.10
license	Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS APPENDIX: How to apply the Apache License to your work. To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives. Copyright [yyyy] [name of copyright owner] Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.
keywords	ai ai-assistant ai-chat ai-interaction anthropic chatglm chatgpt claude cli cohere command-line completion console-application conversation deepseek gemini gpt groq huggingface inference interactive language-model llm llms mistral modelscope nlp ollama openai prompt python-tool sambanova shell-integration siliconflow terminal terminal-interface text-generation vertexai xai
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # YAICLI: Your AI assistant in command line.

<p align="center">
  <img src="artwork/logo.png" width="150" alt="YAICLI Logo" />
</p>

<a href="https://www.producthunt.com/posts/yaicli?embed=true&utm_source=badge-featured&utm_medium=badge&utm_source=badge-yaicli" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=965413&theme=neutral&t=1747386335651" alt="Yaicli - Yaicli&#0058;&#0032;Your&#0032;AI&#0032;assistant&#0032;in&#0032;the&#0032;command&#0032;line&#0046; | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>

[![PyPI version](https://img.shields.io/pypi/v/yaicli?style=for-the-badge)](https://pypi.org/project/yaicli/)
![GitHub License](https://img.shields.io/github/license/belingud/yaicli?style=for-the-badge)
![PyPI - Downloads](https://img.shields.io/pypi/dm/yaicli?logo=pypi&style=for-the-badge)
![Pepy Total Downloads](https://img.shields.io/pepy/dt/yaicli?style=for-the-badge&logo=python)

YAICLI is a powerful yet lightweight command-line AI assistant that brings the capabilities of Large Language Models (
LLMs) like GPT-4o directly to your terminal. Interact with AI through multiple modes: have natural conversations,
generate and execute shell commands, or get quick answers without leaving your workflow.

**Supports both standard and deep reasoning models across all major LLM providers.**

<a href="https://asciinema.org/a/vyreM0n576GjGL2asjI3QzUIY" target="_blank"><img src="https://asciinema.org/a/vyreM0n576GjGL2asjI3QzUIY.svg" width="85%"/></a>

> [!NOTE]
> YAICLI is actively developed. While core functionality is stable, some features may evolve in future releases.

> We support MCP since v0.7.0!
> 
> We support Function Call since v0.5.0!

## ✨ Key Features

### 🔄 Multiple Interaction Modes

- **💬 Chat Mode**: Engage in persistent conversations with full context tracking
- **🚀 Execute Mode**: Generate and safely run OS-specific shell commands
- **⚡ Quick Query**: Get instant answers without entering interactive mode

### 🧠 Smart Environment Awareness

- **Auto-detection**: Identifies your shell (bash/zsh/PowerShell/CMD) and OS
- **Safe Command Execution**: Verification before running any command
- **Flexible Input**: Pipe content directly (`cat log.txt | ai "analyze this"`)

### 🔌 Universal LLM Compatibility

- **OpenAI-Compatible**: Works with any OpenAI-compatible API endpoint
- **Multi-Provider Support**: Support multiple providers

### 💻 Enhanced Terminal Experience

- **Real-time Streaming**: See responses as they're generated with cursor animation
- **Rich History Management**: Manage histories with 500 entries by default
- **Syntax Highlighting**: Beautiful code formatting with customizable themes

### 🛠️ Developer-Friendly

- **Layered Configuration**: Environment variables > Config file > Sensible defaults
- **Debugging Tools**: Verbose mode with detailed API tracing

### 📚 Function Calling & MCP

- **Function Calling**: Enable function/MCP calling in API requests
- **Function Output**: Show the output of functions/MCP

![What is life](artwork/reasoning_example.png)

Full document: https://belingud.github.io/yaicli/

## 📦 Installation

### Prerequisites

- Python 3.10 or higher

### Quick Install

```bash
# Using pip (recommended for most users)
pip install yaicli

# Using pipx (isolated environment)
pipx install yaicli

# Using uv (faster installation)
uv tool install yaicli
```

Yaicli has several optional dependencies group, you can copy below commands to install specific dependencies.

```shell
# install all denpendencies
pip install 'yaicli[all]'

# install with specific provider support
pip instsall 'yaicli[ollama,cohere,doubao,huggingface,gemini,mistral,anthropic]'
```

Install by `uv`.

```shell
# install all denpendencies
uv tool install 'yaicli[all]'

# install with specific provider support
uv tool instsall 'yaicli[ollama,cohere,doubao,huggingface,gemini,mistral,anthropic]'
```

### Install from Source

```bash
git clone https://github.com/belingud/yaicli.git
cd yaicli
pip install .
```

## Buildin Supported Providers

- AI21
- Anthropic/Claude
- Anthropic Bedrock
- Anthropic Vertex
- Cerebras
- Chatglm
- Chuts
- Cohere
- Cohere Badrock
- Cohere Sagemaker
- Deepseek
- Doubao
- Fireworks
- Gemini
- Groq
- Huggingface
- Minimax
- Mistral
- ModelScope
- Ollama
- Openai
- Openai Azure
- Sambanova
- Siliconflow
- Spark
- Targon
- Together
- Vertex ai
- X AI
- Yi
- Unlimited OpenAI-compatible providers

## ⚙️ Configuration

YAICLI uses a simple configuration file to store your preferences and API keys.

### First-time Setup

1. Run `ai` once to generate the default configuration file
2. Edit `~/.config/yaicli/config.ini` to add your API key
3. Customize other settings as needed

### Configuration File Structure

The default configuration file is located at `~/.config/yaicli/config.ini`. You can use `ai --template` to see default

### Configuration Options Reference

| Option                 | Description                                 | Default                  | Env Variable               |
| ---------------------- | ------------------------------------------- | ------------------------ | -------------------------- |
| `PROVIDER`             | LLM provider (openai, claude, cohere, etc.) | `openai`                 | `YAI_PROVIDER`             |
| `BASE_URL`             | API endpoint URL                            | -                        | `YAI_BASE_URL`             |
| `API_KEY`              | Your API key                                | -                        | `YAI_API_KEY`              |
| `MODEL`                | LLM model to use                            | `gpt-4o`                 | `YAI_MODEL`                |
| `DEFAULT_ROLE`         | Default role                                | `DEFAULT`                | `YAI_DEFAULT_ROLE`         |
| `SHELL_NAME`           | Shell type                                  | `auto`                   | `YAI_SHELL_NAME`           |
| `OS_NAME`              | Operating system                            | `auto`                   | `YAI_OS_NAME`              |
| `STREAM`               | Enable streaming                            | `true`                   | `YAI_STREAM`               |
| `TIMEOUT`              | API timeout (seconds)                       | `60`                     | `YAI_TIMEOUT`              |
| `EXTRA_HEADERS`        | Extra headers                               | -                        | `YAI_EXTRA_HEADERS`        |
| `EXTRA_BODY`           | Extra body                                  | -                        | `YAI_EXTRA_BODY`           |
| `REASONING_EFFORT`     | Reasoning effort                            | -                        | `YAI_REASONING_EFFORT`     |
| `INTERACTIVE_ROUND`    | Interactive mode rounds                     | `25`                     | `YAI_INTERACTIVE_ROUND`    |
| `CODE_THEME`           | Syntax highlighting theme                   | `monokai`                | `YAI_CODE_THEME`           |
| `TEMPERATURE`          | Response randomness                         | `0.7`                    | `YAI_TEMPERATURE`          |
| `FREQUENCY_PENALTY`    | Repeat pubnish                              | `0.0`                    | `YAI_FREQUENCY_PENALTY`    |
| `TOP_P`                | Top-p sampling                              | `1.0`                    | `YAI_TOP_P`                |
| `MAX_TOKENS`           | Max response tokens                         | `1024`                   | `YAI_MAX_TOKENS`           |
| `MAX_HISTORY`          | Max history entries                         | `500`                    | `YAI_MAX_HISTORY`          |
| `AUTO_SUGGEST`         | Enable history suggestions                  | `true`                   | `YAI_AUTO_SUGGEST`         |
| `SHOW_REASONING`       | Enable reasoning display                    | `true`                   | `YAI_SHOW_REASONING`       |
| `JUSTIFY`              | Text alignment                              | `default`                | `YAI_JUSTIFY`              |
| `CHAT_HISTORY_DIR`     | Chat history directory                      | `<tempdir>/yaicli/chats` | `YAI_CHAT_HISTORY_DIR`     |
| `MAX_SAVED_CHATS`      | Max saved chats                             | `20`                     | `YAI_MAX_SAVED_CHATS`      |
| `ROLE_MODIFY_WARNING`  | Warn user when modifying role               | `true`                   | `YAI_ROLE_MODIFY_WARNING`  |
| `ENABLE_FUNCTIONS`     | Enable function calling                     | `true`                   | `YAI_ENABLE_FUNCTIONS`     |
| `SHOW_FUNCTION_OUTPUT` | Show function output when calling function  | `true`                   | `YAI_SHOW_FUNCTION_OUTPUT` |
| `ENABLE_MCP`           | Enable MCP tools                            | `false`                  | `YAI_ENABLE_MCP`           |
| `SHOW_MCP_OUTPUT`      | Show MCP output when calling mcp            | `true`                   | `YAI_SHOW_MCP_OUTPUT`      |
| `MAX_TOOL_CALL_DEPTH`  | Max tool calls in one request               | `8`                      | `YAI_MAX_TOOL_CALL_DEPTH`  |


### LLM Provider Configuration

YAICLI works with major LLM providers. The default configuration is set up for OpenAI, but you can easily switch to
other providers.

Note: blank `BASE_URL` (or no `BASE_URL`) means use provider default url.

#### Pre-configured Provider Settings

| Provider                       | BASE_URL                                                  |
| ------------------------------ | --------------------------------------------------------- |
| **OpenAI** (default)           | `https://api.openai.com/v1`                               |
| **Claude** (native API)        | `https://api.anthropic.com/v1`                            |
| **Claude** (OpenAI-compatible) | `https://api.anthropic.com/v1/openai`                     |
| **Cohere**                     | `https://api.cohere.com`                                  |
| **Gemini**                     | `https://generativelanguage.googleapis.com/v1beta/openai` |

> **Note**: Many providers offer OpenAI-compatible endpoints that work with the default settings.
>
> - Google Gemini: https://ai.google.dev/gemini-api/docs/openai
> - Claude: https://docs.anthropic.com/en/api/openai-sdk

If you not sure about base_url or just use the default provider base_url, just leave it blank or delete `BASE_URL`.

```ini
[core]
PROVIDER=cohere
BASE_URL=
API_KEY=xxx
MODEL=command-r-plus
```

#### Openai

Yaicli use `openai` as provider as default provider, `gpt-4o` as default model, you can add your api key to use as it is.

```ini
PROVIDER=openai
BASE_URL=
API_KEY=
MODEL=gpt-4o
```

Extra params:

```ini
# REASONING_EFFORT: [high, midium, low]
REASONING_EFFORT=
```

See official for more details: https://platform.openai.com/docs/guides/reasoning?api-mode=chat

#### Openai Azure

```ini
PROVIDER=openai-azure
BASE_URL=
API_KEY=
MODEL=gpt-4o
```

Support config keys:

```ini
AZURE_AD_TOKEN=
AZURE_ENDPOINT=
AZURE_DEPLOYMENT=
API_VERSION=
```

Support environment variables:

```shell
AZURE_OPENAI_API_KEY=
AZURE_OPENAI_AD_TOKEN=
AZURE_OPENAI_ENDPOINT=
```

If `API_KEY` not set in config, will look for `AZURE_OPENAI_API_KEY` environment variable.

If `AZURE_AD_TOKEN` not set in config, will look for `AZURE_OPENAI_AD_TOKEN` environment variable.

If `BASE_URL` and `AZURE_ENDPOINT` not set in config, will look for `AZURE_OPENAI_ENDPOINT` environment variable.

#### Anghropic/Claude

```ini
PROVIDER=anthropic
API_KEY=
MODEL=claude-sonnet-4-20250514
```

If you want to access **Anthropic bedrock**, you need to set `AWS_SECRET_ACCESS_KEY`, `AWS_ACCESS_KEY_ID`, `AWS_SESSION_TOKEN` and `AWS_REGION` 
in config or environment variables.

```ini
PROVIDER=anthropic-bedrock
AWS_SECRET_ACCESS_KEY=
AWS_ACCESS_KEY_ID=
AWS_SESSION_TOKEN=
AWS_REGION=
MODEL=anthropic.claude-opus-4-20250514-v1:0
```

Support `ANTHROPIC_BEDROCK_BASE_URL` env or `BASE_URL` in config file, with same effect.

Also support **Anthropic vertex** with key `PROJECT_ID` and `CLOUD_ML_REGION` in config or environment variables.

```ini
PROVIDER=anthropic-vertex
PROJECT_ID=
CLOUD_ML_REGION=
```

You can set anthropic base url by `ANTHROPIC_VERTEX_BASE_URL` env, or set `BASE_URL` in config file, same effect.

#### Deepseek

```ini
PROVIDER=deepseek
API_KEY=
MODEL=deepseek-chat
```

#### OpenRouter

```ini
PROVIDER=openrouter
API_KEY=
MODEL=deepseek/deepseek-chat-v3-0324
```

#### Mistral

```ini
PROVIDER=mistral
API_KEY=
MODEL=codestral-latest
```

#### Gemini

Basic config:

```ini
PROVIDER=gemini
API_KEY=
MODEL=gemini-2.5-flash
```

Extra params:

```ini
TOP_K=
PRESENCE_PENALTY=
FREQUENCY_PENALTY=
SEED=
THINKING_BUDGET=
API_VERSION=
BASE_URL=
```

#### Vertex AI

```ini
PROVIDER=vertexai
MODEL=gemini-2.5-flash
PROJECT=
LOCATION=
```

#### Huggingface

Default `HF_PROVIDER` is `auto`.

```ini
HF_PROVIDER=auto
PROVIDER=huggingface
API_KEY=
MODEL=deepseek-ai/DeepSeek-R1-0528
```

See official docs for `HF_PROVIDER`: https://huggingface.co/docs/inference-providers/index

#### Groq

```ini
PROVIDER=groq
API_KEY=
MODEL=llama-3.3-70b-versatile
```

#### XAI

```ini
PROVIDER=xai
API_KEY=
MODEL=grok-3
```

#### Chatglm

```ini
PROVIDER=chatglm
API_KEY=
MODEL=glm-4-plus
```

Extra params:

Check offcial docs: https://bigmodel.cn/dev/api/normal-model/glm-4

```ini
# true or false
DO_SAMPLE=
```

#### Chutes

```ini
PROVIDER=chutes
API_KEY=
MODEL=deepseek-ai/DeepSeek-V3-0324
```

#### Cerebras

```ini
PROVIDER=cerebras
API_KEY=
MODEL=llama3.3-70b
```

#### AI21

```ini
PROVIDER=ai21
API_KEY=
MODEL=jamba-large-1.6
```

#### Sambanova

```ini
PROVIDER=sambanova
API_KEY=
MODEL=DeepSeek-V3-0324
```

Only a few models support tool call as below:

- Meta-Llama-3.1-8B-Instruct
- Meta-Llama-3.1-405B-Instruct
- Meta-Llama-3.3-70B-Instruct
- Llama-4-Scout-17B-16E-Instruct
- DeepSeek-V3-0324

See official docs for more detail: https://docs.sambanova.ai/cloud/docs/capabilities/function-calling

#### ModelScope

```ini
PROVIDER=modelscope
API_KEY=
MODEL=deepseek-ai/DeepSeek-V3-0324
```

#### Inifiniai

```ini
PROVIDER=infiniai
; BASE_URL=https://cloud.infini-ai.com/maas/v1
API_KEY=
MODEL=deepseek-v3
```

#### Siliconflow

```ini
PROVIDER=siliconflow
API_KEY=
MODEL=Qwen/Qwen3-32B
```

#### Yi

```ini
PROVIDER=yi
API_KEY=
MODEL=yi-lightning
```

#### Cohere

You have to install cohere dependencies, `pip install 'yaicli[cohere]'`

```ini
PROVIDER=cohere
API_KEY=
MODEL=command-a-03-2025
```

Check official docs: https://docs.cohere.com/docs/text-gen-quickstart

Support keys:

```ini
ENVIRONMENT=
```

For private deploy and Azure api, you need to set BASE_URL.

```ini
PROVIDER=cohere
API_KEY=
MODEL=command-a-03-2025
BASE_URL=<YOUR_ENDPOINT>
```

For Bedrock and Sagemaker cohere api, you have to set below keys:

See https://docs.cohere.com/docs/text-gen-quickstart.

```ini
PROVIDER=cohere-bedrock
; PROVIDER=cohere-sagemaker
API_KEY=
MODEL=command-a-03-2025

AWS_REGION=xx
AWS_ACCESS_KEY_ID=xx
AWS_SECRET_ACCESS_KEY=xx
AWS_SESSION_TOKEN=xx
```

Note `MODEL` for Sagemaker should be endpoint name

```ini
MODEL=<YOUR_ENDPOINT_NAME>
```

#### Doubao

You have to install doubao dependencies, `pip install 'yaicli[doubao]'`

Use doubao OpenAI compatible api, you can just set `API_KEY`.

```ini
PROVIDER=doubao
API_KEY=
MODEL=doubao-1-5-lite-32k-250115
```

If you are using access key, you have to set `AK` and `SK`.

```ini
PROVIDER=doubao
MODEL=doubao-1-5-lite-32k-250115
AK=XXX
SK=XXX
```

#### Ollama

You have to install ollama dependencies, `pip install 'yaicli[ollama]'`

```ini
PROVIDER=ollama
; BASE_URL=http://localhost:11434
MODEL=qwen3:32b
```

Support options:

```ini
TEMPERATURE=
TOP_P=
SEED=
NUM_PREDICT=
NUM_CTX=
NUM_BATCH=
NUM_GPU=
MAIN_GPU=
LOW_VRAM=
F16_KV=
LOGITS_ALL=
VOCAB_ONLY=
USE_MMAP=
USE_MLOCK=
NUM_THREAD=
```

NOTE: Ollama provider not support extra body

#### Bailian

> Only support model API call, not support application API call.

```ini
PROVIDER=bailian
API_KEY=
MODEL=qwen-plus
```

#### Bailian Intl

Bailian international platform.

```ini
PROVIDER=bailian-intl
API_KEY=
MODEL=qwen-plus
```

#### Nvida nim

```ini
PROVIDER=nvida
API_KEY=
MODEL=qwen/qwen3-235b-a22b
EXTRA_BODY={"chat_template_kwargs": {"thinking": false}}
```

> `chat_template_kwargs` is for Qwen3 and ibm/granite models, you disable thinking as above config.

#### Together

Using together openai-compatible capabilities

```ini
PROVIDER=together
API_KEY=
MODEL=Qwen/Qwen3-235B-A22B-fp8-tput
```

#### Spark

```ini
PROVIDER=spark
API_KEY=
MODEL=4.0Ultra
```

Or you can use your `APP_ID` and `API_SECRET`.

```ini
PROVIDER=spark
APP_ID=
APP_SECRET=
MODEL=4.0Ultra
```


## 🚀 Usage

### Quick Start

```bash
# Get a quick answer
ai "What is the capital of France?"

# Start an interactive chat session
ai --chat

# Generate and execute shell commands
ai --shell "Create a backup of my Documents folder"

# Generate code snippets, default in Python
ai --code "Write a Python function to sort a list"

# Analyze code from a file
cat app.py | ai "Explain what this code does"

# Debug with verbose mode
ai --verbose "Explain quantum computing"
```

### Interactive Mode Features

<table>
<tr>
<td width="50%">

**Commands**

- `/help|?` - Show help message
- `/clear` - Clear conversation history
- `/his` - Show command history
- `/list` - List saved chats
- `/save <title>` - Save current chat with title
- `/load <index>` - Load a saved chat
- `/del <index>` - Delete a saved chat
- `/exit` - Exit the application
- `/mode chat|exec` - Switch modes

**Keyboard Shortcuts**

- `Tab` - Toggle between Chat/Execute modes
- `Ctrl+C` or `Ctrl+D` - Exit
- `Ctrl+R` - Search history
- `↑/↓` - Navigate through history

</td>
<td width="50%">

**Chat Mode** (💬)

- Natural conversations with context
- Markdown and code formatting
- Reasoning display for complex queries

**Execute Mode** (🚀)

- Generate shell commands from descriptions
- Review commands before execution
- Edit commands before running
- Safe execution with confirmation

</td>
</tr>
</table>

### Chat Persistent

The `<PROMPT>` parameter in the chat mode will be used as a title to persist the chat content to the file system, with
the save directory being a temporary directory, which may vary between machines, and it is determined on the first run.

If the `<PROMPT>` parameter is not specified when entering `chat` mode, the session will be treated as a temporary
session and will not be persisted. Of course, you can also manually call the `/save <title>` command to save during the
chat.
When you run the same `chat` command again, the previous session will be automatically loaded.

```bash
$ ai --chat "meaning of life"
```

> !NOTE: Chat mode is not supported when you redirect input to `ai` command.
>
> ```bash
> $ cat error.log | ai --chat "Explain this error"
> ```
>
> The above command will be parsed as `ai "cat error.log | ai "Explain this error"`.

**Start a temporary chat session**

```bash
$ ai --chat
```

**Start a persistent chat session**

```bash
$ ai --chat "check disk usage"
```

**Load a saved chat session**

```bash
$ ai --chat hello
Chat title: hello

 ██    ██  █████  ██  ██████ ██      ██
  ██  ██  ██   ██ ██ ██      ██      ██
   ████   ███████ ██ ██      ██      ██
    ██    ██   ██ ██ ██      ██      ██
    ██    ██   ██ ██  ██████ ███████ ██

Welcome to YAICLI!
Current: Persistent Session: hello
Press TAB to switch mode
/clear             : Clear chat history
/his               : Show chat history
/list              : List saved chats
/save <title>      : Save current chat
/load <index>      : Load a saved chat
/del <index>       : Delete a saved chat
/exit|Ctrl+D|Ctrl+C: Exit
/mode chat|exec    : Switch mode (Case insensitive)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
 💬 > /his
Chat History:
1 User: hi
    Assistant:
    Hello! How can I assist you today?
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
 💬 >
```

### Input Methods

**Direct Input**

```bash
ai "What is the capital of France?"
```

**Piped Input**

```bash
echo "What is the capital of France?" | ai
```

**File Analysis**

```bash
cat demo.py | ai "Explain this code"
```

**Combined Input**

```bash
cat error.log | ai "Why am I getting these errors in my Python app?"
```

## 📱 Examples

### Quick Answer Mode

```bash
$ ai "What is the capital of France?"
Assistant:
The capital of France is Paris.
```

### Command Generation & Execution

```bash
$ ai -s 'Check the current directory size'
Assistant:
du -sh .
╭─ Command ─╮
│ du -sh .  │
╰───────────╯
Execute command? [e]dit, [y]es, [n]o (n): e
Edit command, press enter to execute:
du -sh ./
Output:
109M    ./
```

### Code Generation

In code mode, select the language for code generation. If none is specified, Python is the default.

The `--code` mode outputs plain text, making it easy to copy, paste, or redirect to a file, especially when using the standard model.

When using a deep reasoning model, the thinking content is displayed with syntax highlighting. To disable this, use the `--no-show-reasoning` option or set `SHOW_REASONING` to `false` in the configuration.

```bash
$ ai --code 'Write a fib generator'
def fib_generator():
    a, b = 0, 1
    while True:
        yield a
        a, b = b, a + b
```

### Chat Mode Example

```bash
$ ai --chat
Starting a temporary chat session (will not be saved automatically)

 ██    ██  █████  ██  ██████ ██      ██
  ██  ██  ██   ██ ██ ██      ██      ██
   ████   ███████ ██ ██      ██      ██
    ██    ██   ██ ██ ██      ██      ██
    ██    ██   ██ ██  ██████ ███████ ██

Welcome to YAICLI!
Current: Temporary Session (use /save to make persistent)
Press TAB to switch mode
/clear             : Clear chat history
/his               : Show chat history
/list              : List saved chats
/save <title>      : Save current chat
/load <index>      : Load a saved chat
/del <index>       : Delete a saved chat
!<command>         : Execute shell command directly (e.g., !ls -al)
/exit|Ctrl+D|Ctrl+C: Exit
/mode chat|exec    : Switch mode (Case insensitive)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
 💬 > Tell me about the solar system

Assistant:
Solar System Overview

 • Central Star: The Sun (99% of system mass, nuclear fusion).
 • Planets: 8 total.
    • Terrestrial (rocky): Mercury, Venus, Earth, Mars.
    • Gas Giants: Jupiter, Saturn.
    • Ice Giants: Uranus, Neptune.
 • Moons: Over 200 (e.g., Earth: 1, Jupiter: 95).
 • Smaller Bodies:
    • Asteroids (between Mars/Venus), comets ( icy, distant), * dwarf planets* (Pluto, Ceres).
 • Oort Cloud: spherical shell of icy objects ~1–100,000天文單位 (AU) from Sun).
 • Heliosphere: Solar wind boundary protecting Earth from cosmic radiation.

Key Fact: Earth is the only confirmed habitable planet.

🚀 > Check the current directory size
Assistant:
du -sh .
╭─ Suggest Command ─╮
│ du -sh .          │
╰───────────────────╯
Execute command? [e]dit, [y]es, [n]o (n): e
Edit command: du -sh ./
--- Executing ---
 55M    ./
--- Finished ---
🚀 >
```

### Execute Mode Example

```bash
$ ai --shell "Find all PDF files in my Downloads folder"
Assistant:
find ~/Downloads -type f -name "*.pdf"
╭─ Suggest Command ───────────────────────╮
│ find ~/Downloads -type f -iname "*.pdf" │
╰─────────────────────────────────────────╯
Execute command? [e]dit, [y]es, [n]o (n): y
Output:

/Users/username/Downloads/document1.pdf
/Users/username/Downloads/report.pdf
...
```

### Code Mode Example

```bash
$ ai --code "write a fib generator" --model deepseek-r1
```

![fib code example](artwork/reasoning_code_example.png)

### Function Call

To use function call, you need to install default functions by `ai --install-functions`.
After that, you can check the functions by `ai --list-functions`.
You can also define your own functions by adding them to the config folder in `~/.config/yaicli/functions/` (`C:\Users\<user>\.config\yaicli\functions` on Windows).

`--enable-functions` option is corresponds to the configuration key `ENABLE_FUNCTIONS`.

```shell
ai 'check the current dir total size' --enable-functions
Assistant:
Thinking:

▌ Okay, the user wants to check the current directory's total size. Hmm, how do I do that in macOS with zsh?
▌ I remember that the command to get disk usage is usually 'du'. But wait, the default 'du' might not give the total size of the
▌ current directory directly. Let me think. Oh right, if I use 'du -sh' with the current directory, that should give the total size
▌ in human-readable format.
▌ Wait, but sometimes the -s option summarizes the directory. So 'du -sh .' would calculate the total size of the current directory
▌ and its subdirectories. That should work. Let me confirm the syntax. Yeah, 'du -sh .' is the right command here.
▌ The user is using zsh, but the 'du' command is standard, so it should be available. I need to execute this shell command. The
▌ function provided is execute_shell_command, so I'll call that with the shell command 'du -sh .' as the argument.
▌ I should make sure the parameters are correctly formatted. The function requires a shell_command string. Alright, that's all.
▌ Let's generate the tool call.

{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":null,"audio":null,"tool_calls":[{"id":"call_202505141526
36cc3f776ae8f14b56_0","index":0,"type":"function","function":{"name":"execute_shell_command","arguments":"{"shell_command": "du -sh
."}","outputs":null},"code_interpreter":null,"retrieval":null,"drawing_tool":null,"web_browser":null,"search_intent":null,"search_resu
lt":null}],"tool_call_id":null,"attachments":null,"metadata":null}}
@Function call: execute_shell_command({"shell_command": "du -sh ."})
╭─ Function output ─────╮
│ Exit code: 0, Output: │
│ 156M    .             │
│                       │
╰───────────────────────╯
Thinking:

▌ Okay, the user asked to check the current directory's total size. I used the 'du -sh .' command, which stands for disk usage,
▌ summarize, and current directory. The output was "156M". So I need to present this in a concise way.
▌ First, confirm the command was executed. Then, report the result clearly. Since the user didn't ask for extra details, keep it
▌ simple. Just state the total size as 156MB. Maybe mention the command used for transparency. Alright, that should cover it without
▌ overcomplicating.

Current directory size: 156M (using du -sh .).
```

### MCP

Add your MCP config in `~/.config/yaicli/mcp.json` (`C:\Users\<user>\.config\yaicli\mcp.json` on Windows.).

`--enable-mcp` option is corresponds to the configuration key `ENABLE_MCP`.

Example:

```shell
ai 'What is the latest exchange rate between the BTC and the US dollar?' --enable-mcp --show-mcp-output

Assistant:

@Mcp call: bing_search({"query": "latest exchange rate between BTC and US dollar"})
╭─ Mcp output ──────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ [                                                                                                                         │
│   {                                                                                                                       │
│     "id": "result_1751024997243_0",                                                                                       │
│     "title": "BTC to USD - Bitcoin to US Dollar Conversion - Exchange Rates",                                             │
│     "link": "https://www.exchange-rates.org/converter/btc-usd",                                                           │
│     "snippet": "11 小时之前 · 1 Bitcoin = 107,304 US Dollars as of June 27, 2025 03:00 AM UTC. You can get live exchange  │
│ rates between Bitcoin and US Dollars using exchange-rates.org, which aggregates …"                                        │
│   },                                                                                                                      │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
Here are some current exchange rates for Bitcoin (BTC) to US Dollar (USD):                                                   

 1 Exchange-Rates.org:                                                                                                       
   ₿1 Bitcoin = 💵107,304 US Dollars (as of June 27, 2025, 03:00 AM UTC).                                                    
   Link                                                                                                                      
 2 BTC.CurrencyRate.Today:                                                                                                   
   Live Bitcoin to US Dollars exchange rate.                                                                                 
   Link                                                                                                                      
 3 Xe.com:                                                                                                                   
   Latest conversion rate and information about Bitcoin to US Dollars.                                                       
   Link                                                                                                                      
 4 BestExchangeRates.com:                                                                                                    
   Current BTC to USD market data, including charts and historic rates.                                                      
   Link                                                                                                                      
 5 Investing.com:                                                                                                            
   Bitcoin price analysis and live BTC to USD updates.                                                                       
   Link                                                                                                                      

For the most accurate and up-to-date rate, I recommend checking one of these sources directly.                               
```

![mcp](artwork/mcp_example.png)


## 💻 Technical Details

### Architecture

YAICLI is designed with a modular architecture that separates concerns and makes the codebase maintainable:

- **CLI Module**: Handles user interaction and command parsing
- **API Client**: Manages communication with LLM providers
- **Config Manager**: Handles layered configuration
- **History Manager**: Maintains conversation history with LRU functionality
- **Printer**: Formats and displays responses with rich formatting

### Dependencies

| Library                                                         | Purpose                                            |
| --------------------------------------------------------------- | -------------------------------------------------- |
| [Typer](https://typer.tiangolo.com/)                            | Command-line interface with type hints             |
| [Rich](https://rich.readthedocs.io/)                            | Terminal formatting and beautiful display          |
| [prompt_toolkit](https://python-prompt-toolkit.readthedocs.io/) | Interactive input with history and auto-completion |
| [json-repair](https://github.com/mangiucugna/json_repair)       | Repair llm function call arguments                 |

## 👨‍💻 Contributing

Contributions are welcome! Here's how you can help:

- **Bug Reports**: Open an issue describing the bug and how to reproduce it
- **Feature Requests**: Suggest new features or improvements
- **Code Contributions**: Submit a PR with your changes
- **Documentation**: Help improve or translate the documentation

## 📃 License

[Apache License 2.0](LICENSE)

---

<p align="center"><i>YAICLI - Your AI Command Line Interface</i></p>

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "yaicli",
    "maintainer": null,
    "docs_url": null,
    "requires_python": ">=3.10",
    "maintainer_email": null,
    "keywords": "ai, ai-assistant, ai-chat, ai-interaction, anthropic, chatglm, chatgpt, claude, cli, cohere, command-line, completion, console-application, conversation, deepseek, gemini, gpt, groq, huggingface, inference, interactive, language-model, llm, llms, mistral, modelscope, nlp, ollama, openai, prompt, python-tool, sambanova, shell-integration, siliconflow, terminal, terminal-interface, text-generation, vertexai, xai",
    "author": null,
    "author_email": "belingud <im.victor@qq.com>",
    "download_url": "https://files.pythonhosted.org/packages/0d/9f/64a3ea13f320ecd158102c4b02ea668111a39f4530bf29f25567e22bcded/yaicli-0.8.10.tar.gz",
    "platform": null,
    "description": "# YAICLI: Your AI assistant in command line.\n\n<p align=\"center\">\n  <img src=\"artwork/logo.png\" width=\"150\" alt=\"YAICLI Logo\" />\n</p>\n\n<a href=\"https://www.producthunt.com/posts/yaicli?embed=true&utm_source=badge-featured&utm_medium=badge&utm_source=badge-yaicli\" target=\"_blank\"><img src=\"https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=965413&theme=neutral&t=1747386335651\" alt=\"Yaicli - Yaicli&#0058;&#0032;Your&#0032;AI&#0032;assistant&#0032;in&#0032;the&#0032;command&#0032;line&#0046; | Product Hunt\" style=\"width: 250px; height: 54px;\" width=\"250\" height=\"54\" /></a>\n\n[![PyPI version](https://img.shields.io/pypi/v/yaicli?style=for-the-badge)](https://pypi.org/project/yaicli/)\n![GitHub License](https://img.shields.io/github/license/belingud/yaicli?style=for-the-badge)\n![PyPI - Downloads](https://img.shields.io/pypi/dm/yaicli?logo=pypi&style=for-the-badge)\n![Pepy Total Downloads](https://img.shields.io/pepy/dt/yaicli?style=for-the-badge&logo=python)\n\nYAICLI is a powerful yet lightweight command-line AI assistant that brings the capabilities of Large Language Models (\nLLMs) like GPT-4o directly to your terminal. Interact with AI through multiple modes: have natural conversations,\ngenerate and execute shell commands, or get quick answers without leaving your workflow.\n\n**Supports both standard and deep reasoning models across all major LLM providers.**\n\n<a href=\"https://asciinema.org/a/vyreM0n576GjGL2asjI3QzUIY\" target=\"_blank\"><img src=\"https://asciinema.org/a/vyreM0n576GjGL2asjI3QzUIY.svg\" width=\"85%\"/></a>\n\n> [!NOTE]\n> YAICLI is actively developed. While core functionality is stable, some features may evolve in future releases.\n\n> We support MCP since v0.7.0!\n> \n> We support Function Call since v0.5.0!\n\n## \u2728 Key Features\n\n### \ud83d\udd04 Multiple Interaction Modes\n\n- **\ud83d\udcac Chat Mode**: Engage in persistent conversations with full context tracking\n- **\ud83d\ude80 Execute Mode**: Generate and safely run OS-specific shell commands\n- **\u26a1 Quick Query**: Get instant answers without entering interactive mode\n\n### \ud83e\udde0 Smart Environment Awareness\n\n- **Auto-detection**: Identifies your shell (bash/zsh/PowerShell/CMD) and OS\n- **Safe Command Execution**: Verification before running any command\n- **Flexible Input**: Pipe content directly (`cat log.txt | ai \"analyze this\"`)\n\n### \ud83d\udd0c Universal LLM Compatibility\n\n- **OpenAI-Compatible**: Works with any OpenAI-compatible API endpoint\n- **Multi-Provider Support**: Support multiple providers\n\n### \ud83d\udcbb Enhanced Terminal Experience\n\n- **Real-time Streaming**: See responses as they're generated with cursor animation\n- **Rich History Management**: Manage histories with 500 entries by default\n- **Syntax Highlighting**: Beautiful code formatting with customizable themes\n\n### \ud83d\udee0\ufe0f Developer-Friendly\n\n- **Layered Configuration**: Environment variables > Config file > Sensible defaults\n- **Debugging Tools**: Verbose mode with detailed API tracing\n\n### \ud83d\udcda Function Calling & MCP\n\n- **Function Calling**: Enable function/MCP calling in API requests\n- **Function Output**: Show the output of functions/MCP\n\n![What is life](artwork/reasoning_example.png)\n\nFull document: https://belingud.github.io/yaicli/\n\n## \ud83d\udce6 Installation\n\n### Prerequisites\n\n- Python 3.10 or higher\n\n### Quick Install\n\n```bash\n# Using pip (recommended for most users)\npip install yaicli\n\n# Using pipx (isolated environment)\npipx install yaicli\n\n# Using uv (faster installation)\nuv tool install yaicli\n```\n\nYaicli has several optional dependencies group, you can copy below commands to install specific dependencies.\n\n```shell\n# install all denpendencies\npip install 'yaicli[all]'\n\n# install with specific provider support\npip instsall 'yaicli[ollama,cohere,doubao,huggingface,gemini,mistral,anthropic]'\n```\n\nInstall by `uv`.\n\n```shell\n# install all denpendencies\nuv tool install 'yaicli[all]'\n\n# install with specific provider support\nuv tool instsall 'yaicli[ollama,cohere,doubao,huggingface,gemini,mistral,anthropic]'\n```\n\n### Install from Source\n\n```bash\ngit clone https://github.com/belingud/yaicli.git\ncd yaicli\npip install .\n```\n\n## Buildin Supported Providers\n\n- AI21\n- Anthropic/Claude\n- Anthropic Bedrock\n- Anthropic Vertex\n- Cerebras\n- Chatglm\n- Chuts\n- Cohere\n- Cohere Badrock\n- Cohere Sagemaker\n- Deepseek\n- Doubao\n- Fireworks\n- Gemini\n- Groq\n- Huggingface\n- Minimax\n- Mistral\n- ModelScope\n- Ollama\n- Openai\n- Openai Azure\n- Sambanova\n- Siliconflow\n- Spark\n- Targon\n- Together\n- Vertex ai\n- X AI\n- Yi\n- Unlimited OpenAI-compatible providers\n\n## \u2699\ufe0f Configuration\n\nYAICLI uses a simple configuration file to store your preferences and API keys.\n\n### First-time Setup\n\n1. Run `ai` once to generate the default configuration file\n2. Edit `~/.config/yaicli/config.ini` to add your API key\n3. Customize other settings as needed\n\n### Configuration File Structure\n\nThe default configuration file is located at `~/.config/yaicli/config.ini`. You can use `ai --template` to see default\n\n### Configuration Options Reference\n\n| Option                 | Description                                 | Default                  | Env Variable               |\n| ---------------------- | ------------------------------------------- | ------------------------ | -------------------------- |\n| `PROVIDER`             | LLM provider (openai, claude, cohere, etc.) | `openai`                 | `YAI_PROVIDER`             |\n| `BASE_URL`             | API endpoint URL                            | -                        | `YAI_BASE_URL`             |\n| `API_KEY`              | Your API key                                | -                        | `YAI_API_KEY`              |\n| `MODEL`                | LLM model to use                            | `gpt-4o`                 | `YAI_MODEL`                |\n| `DEFAULT_ROLE`         | Default role                                | `DEFAULT`                | `YAI_DEFAULT_ROLE`         |\n| `SHELL_NAME`           | Shell type                                  | `auto`                   | `YAI_SHELL_NAME`           |\n| `OS_NAME`              | Operating system                            | `auto`                   | `YAI_OS_NAME`              |\n| `STREAM`               | Enable streaming                            | `true`                   | `YAI_STREAM`               |\n| `TIMEOUT`              | API timeout (seconds)                       | `60`                     | `YAI_TIMEOUT`              |\n| `EXTRA_HEADERS`        | Extra headers                               | -                        | `YAI_EXTRA_HEADERS`        |\n| `EXTRA_BODY`           | Extra body                                  | -                        | `YAI_EXTRA_BODY`           |\n| `REASONING_EFFORT`     | Reasoning effort                            | -                        | `YAI_REASONING_EFFORT`     |\n| `INTERACTIVE_ROUND`    | Interactive mode rounds                     | `25`                     | `YAI_INTERACTIVE_ROUND`    |\n| `CODE_THEME`           | Syntax highlighting theme                   | `monokai`                | `YAI_CODE_THEME`           |\n| `TEMPERATURE`          | Response randomness                         | `0.7`                    | `YAI_TEMPERATURE`          |\n| `FREQUENCY_PENALTY`    | Repeat pubnish                              | `0.0`                    | `YAI_FREQUENCY_PENALTY`    |\n| `TOP_P`                | Top-p sampling                              | `1.0`                    | `YAI_TOP_P`                |\n| `MAX_TOKENS`           | Max response tokens                         | `1024`                   | `YAI_MAX_TOKENS`           |\n| `MAX_HISTORY`          | Max history entries                         | `500`                    | `YAI_MAX_HISTORY`          |\n| `AUTO_SUGGEST`         | Enable history suggestions                  | `true`                   | `YAI_AUTO_SUGGEST`         |\n| `SHOW_REASONING`       | Enable reasoning display                    | `true`                   | `YAI_SHOW_REASONING`       |\n| `JUSTIFY`              | Text alignment                              | `default`                | `YAI_JUSTIFY`              |\n| `CHAT_HISTORY_DIR`     | Chat history directory                      | `<tempdir>/yaicli/chats` | `YAI_CHAT_HISTORY_DIR`     |\n| `MAX_SAVED_CHATS`      | Max saved chats                             | `20`                     | `YAI_MAX_SAVED_CHATS`      |\n| `ROLE_MODIFY_WARNING`  | Warn user when modifying role               | `true`                   | `YAI_ROLE_MODIFY_WARNING`  |\n| `ENABLE_FUNCTIONS`     | Enable function calling                     | `true`                   | `YAI_ENABLE_FUNCTIONS`     |\n| `SHOW_FUNCTION_OUTPUT` | Show function output when calling function  | `true`                   | `YAI_SHOW_FUNCTION_OUTPUT` |\n| `ENABLE_MCP`           | Enable MCP tools                            | `false`                  | `YAI_ENABLE_MCP`           |\n| `SHOW_MCP_OUTPUT`      | Show MCP output when calling mcp            | `true`                   | `YAI_SHOW_MCP_OUTPUT`      |\n| `MAX_TOOL_CALL_DEPTH`  | Max tool calls in one request               | `8`                      | `YAI_MAX_TOOL_CALL_DEPTH`  |\n\n\n### LLM Provider Configuration\n\nYAICLI works with major LLM providers. The default configuration is set up for OpenAI, but you can easily switch to\nother providers.\n\nNote: blank `BASE_URL` (or no `BASE_URL`) means use provider default url.\n\n#### Pre-configured Provider Settings\n\n| Provider                       | BASE_URL                                                  |\n| ------------------------------ | --------------------------------------------------------- |\n| **OpenAI** (default)           | `https://api.openai.com/v1`                               |\n| **Claude** (native API)        | `https://api.anthropic.com/v1`                            |\n| **Claude** (OpenAI-compatible) | `https://api.anthropic.com/v1/openai`                     |\n| **Cohere**                     | `https://api.cohere.com`                                  |\n| **Gemini**                     | `https://generativelanguage.googleapis.com/v1beta/openai` |\n\n> **Note**: Many providers offer OpenAI-compatible endpoints that work with the default settings.\n>\n> - Google Gemini: https://ai.google.dev/gemini-api/docs/openai\n> - Claude: https://docs.anthropic.com/en/api/openai-sdk\n\nIf you not sure about base_url or just use the default provider base_url, just leave it blank or delete `BASE_URL`.\n\n```ini\n[core]\nPROVIDER=cohere\nBASE_URL=\nAPI_KEY=xxx\nMODEL=command-r-plus\n```\n\n#### Openai\n\nYaicli use `openai` as provider as default provider, `gpt-4o` as default model, you can add your api key to use as it is.\n\n```ini\nPROVIDER=openai\nBASE_URL=\nAPI_KEY=\nMODEL=gpt-4o\n```\n\nExtra params:\n\n```ini\n# REASONING_EFFORT: [high, midium, low]\nREASONING_EFFORT=\n```\n\nSee official for more details: https://platform.openai.com/docs/guides/reasoning?api-mode=chat\n\n#### Openai Azure\n\n```ini\nPROVIDER=openai-azure\nBASE_URL=\nAPI_KEY=\nMODEL=gpt-4o\n```\n\nSupport config keys:\n\n```ini\nAZURE_AD_TOKEN=\nAZURE_ENDPOINT=\nAZURE_DEPLOYMENT=\nAPI_VERSION=\n```\n\nSupport environment variables:\n\n```shell\nAZURE_OPENAI_API_KEY=\nAZURE_OPENAI_AD_TOKEN=\nAZURE_OPENAI_ENDPOINT=\n```\n\nIf `API_KEY` not set in config, will look for `AZURE_OPENAI_API_KEY` environment variable.\n\nIf `AZURE_AD_TOKEN` not set in config, will look for `AZURE_OPENAI_AD_TOKEN` environment variable.\n\nIf `BASE_URL` and `AZURE_ENDPOINT` not set in config, will look for `AZURE_OPENAI_ENDPOINT` environment variable.\n\n#### Anghropic/Claude\n\n```ini\nPROVIDER=anthropic\nAPI_KEY=\nMODEL=claude-sonnet-4-20250514\n```\n\nIf you want to access **Anthropic bedrock**, you need to set `AWS_SECRET_ACCESS_KEY`, `AWS_ACCESS_KEY_ID`, `AWS_SESSION_TOKEN` and `AWS_REGION` \nin config or environment variables.\n\n```ini\nPROVIDER=anthropic-bedrock\nAWS_SECRET_ACCESS_KEY=\nAWS_ACCESS_KEY_ID=\nAWS_SESSION_TOKEN=\nAWS_REGION=\nMODEL=anthropic.claude-opus-4-20250514-v1:0\n```\n\nSupport `ANTHROPIC_BEDROCK_BASE_URL` env or `BASE_URL` in config file, with same effect.\n\nAlso support **Anthropic vertex** with key `PROJECT_ID` and `CLOUD_ML_REGION` in config or environment variables.\n\n```ini\nPROVIDER=anthropic-vertex\nPROJECT_ID=\nCLOUD_ML_REGION=\n```\n\nYou can set anthropic base url by `ANTHROPIC_VERTEX_BASE_URL` env, or set `BASE_URL` in config file, same effect.\n\n#### Deepseek\n\n```ini\nPROVIDER=deepseek\nAPI_KEY=\nMODEL=deepseek-chat\n```\n\n#### OpenRouter\n\n```ini\nPROVIDER=openrouter\nAPI_KEY=\nMODEL=deepseek/deepseek-chat-v3-0324\n```\n\n#### Mistral\n\n```ini\nPROVIDER=mistral\nAPI_KEY=\nMODEL=codestral-latest\n```\n\n#### Gemini\n\nBasic config:\n\n```ini\nPROVIDER=gemini\nAPI_KEY=\nMODEL=gemini-2.5-flash\n```\n\nExtra params:\n\n```ini\nTOP_K=\nPRESENCE_PENALTY=\nFREQUENCY_PENALTY=\nSEED=\nTHINKING_BUDGET=\nAPI_VERSION=\nBASE_URL=\n```\n\n#### Vertex AI\n\n```ini\nPROVIDER=vertexai\nMODEL=gemini-2.5-flash\nPROJECT=\nLOCATION=\n```\n\n#### Huggingface\n\nDefault `HF_PROVIDER` is `auto`.\n\n```ini\nHF_PROVIDER=auto\nPROVIDER=huggingface\nAPI_KEY=\nMODEL=deepseek-ai/DeepSeek-R1-0528\n```\n\nSee official docs for `HF_PROVIDER`: https://huggingface.co/docs/inference-providers/index\n\n#### Groq\n\n```ini\nPROVIDER=groq\nAPI_KEY=\nMODEL=llama-3.3-70b-versatile\n```\n\n#### XAI\n\n```ini\nPROVIDER=xai\nAPI_KEY=\nMODEL=grok-3\n```\n\n#### Chatglm\n\n```ini\nPROVIDER=chatglm\nAPI_KEY=\nMODEL=glm-4-plus\n```\n\nExtra params:\n\nCheck offcial docs: https://bigmodel.cn/dev/api/normal-model/glm-4\n\n```ini\n# true or false\nDO_SAMPLE=\n```\n\n#### Chutes\n\n```ini\nPROVIDER=chutes\nAPI_KEY=\nMODEL=deepseek-ai/DeepSeek-V3-0324\n```\n\n#### Cerebras\n\n```ini\nPROVIDER=cerebras\nAPI_KEY=\nMODEL=llama3.3-70b\n```\n\n#### AI21\n\n```ini\nPROVIDER=ai21\nAPI_KEY=\nMODEL=jamba-large-1.6\n```\n\n#### Sambanova\n\n```ini\nPROVIDER=sambanova\nAPI_KEY=\nMODEL=DeepSeek-V3-0324\n```\n\nOnly a few models support tool call as below:\n\n- Meta-Llama-3.1-8B-Instruct\n- Meta-Llama-3.1-405B-Instruct\n- Meta-Llama-3.3-70B-Instruct\n- Llama-4-Scout-17B-16E-Instruct\n- DeepSeek-V3-0324\n\nSee official docs for more detail: https://docs.sambanova.ai/cloud/docs/capabilities/function-calling\n\n#### ModelScope\n\n```ini\nPROVIDER=modelscope\nAPI_KEY=\nMODEL=deepseek-ai/DeepSeek-V3-0324\n```\n\n#### Inifiniai\n\n```ini\nPROVIDER=infiniai\n; BASE_URL=https://cloud.infini-ai.com/maas/v1\nAPI_KEY=\nMODEL=deepseek-v3\n```\n\n#### Siliconflow\n\n```ini\nPROVIDER=siliconflow\nAPI_KEY=\nMODEL=Qwen/Qwen3-32B\n```\n\n#### Yi\n\n```ini\nPROVIDER=yi\nAPI_KEY=\nMODEL=yi-lightning\n```\n\n#### Cohere\n\nYou have to install cohere dependencies, `pip install 'yaicli[cohere]'`\n\n```ini\nPROVIDER=cohere\nAPI_KEY=\nMODEL=command-a-03-2025\n```\n\nCheck official docs: https://docs.cohere.com/docs/text-gen-quickstart\n\nSupport keys:\n\n```ini\nENVIRONMENT=\n```\n\nFor private deploy and Azure api, you need to set BASE_URL.\n\n```ini\nPROVIDER=cohere\nAPI_KEY=\nMODEL=command-a-03-2025\nBASE_URL=<YOUR_ENDPOINT>\n```\n\nFor Bedrock and Sagemaker cohere api, you have to set below keys:\n\nSee https://docs.cohere.com/docs/text-gen-quickstart.\n\n```ini\nPROVIDER=cohere-bedrock\n; PROVIDER=cohere-sagemaker\nAPI_KEY=\nMODEL=command-a-03-2025\n\nAWS_REGION=xx\nAWS_ACCESS_KEY_ID=xx\nAWS_SECRET_ACCESS_KEY=xx\nAWS_SESSION_TOKEN=xx\n```\n\nNote `MODEL` for Sagemaker should be endpoint name\n\n```ini\nMODEL=<YOUR_ENDPOINT_NAME>\n```\n\n#### Doubao\n\nYou have to install doubao dependencies, `pip install 'yaicli[doubao]'`\n\nUse doubao OpenAI compatible api, you can just set `API_KEY`.\n\n```ini\nPROVIDER=doubao\nAPI_KEY=\nMODEL=doubao-1-5-lite-32k-250115\n```\n\nIf you are using access key, you have to set `AK` and `SK`.\n\n```ini\nPROVIDER=doubao\nMODEL=doubao-1-5-lite-32k-250115\nAK=XXX\nSK=XXX\n```\n\n#### Ollama\n\nYou have to install ollama dependencies, `pip install 'yaicli[ollama]'`\n\n```ini\nPROVIDER=ollama\n; BASE_URL=http://localhost:11434\nMODEL=qwen3:32b\n```\n\nSupport options:\n\n```ini\nTEMPERATURE=\nTOP_P=\nSEED=\nNUM_PREDICT=\nNUM_CTX=\nNUM_BATCH=\nNUM_GPU=\nMAIN_GPU=\nLOW_VRAM=\nF16_KV=\nLOGITS_ALL=\nVOCAB_ONLY=\nUSE_MMAP=\nUSE_MLOCK=\nNUM_THREAD=\n```\n\nNOTE: Ollama provider not support extra body\n\n#### Bailian\n\n> Only support model API call, not support application API call.\n\n```ini\nPROVIDER=bailian\nAPI_KEY=\nMODEL=qwen-plus\n```\n\n#### Bailian Intl\n\nBailian international platform.\n\n```ini\nPROVIDER=bailian-intl\nAPI_KEY=\nMODEL=qwen-plus\n```\n\n#### Nvida nim\n\n```ini\nPROVIDER=nvida\nAPI_KEY=\nMODEL=qwen/qwen3-235b-a22b\nEXTRA_BODY={\"chat_template_kwargs\": {\"thinking\": false}}\n```\n\n> `chat_template_kwargs` is for Qwen3 and ibm/granite models, you disable thinking as above config.\n\n#### Together\n\nUsing together openai-compatible capabilities\n\n```ini\nPROVIDER=together\nAPI_KEY=\nMODEL=Qwen/Qwen3-235B-A22B-fp8-tput\n```\n\n#### Spark\n\n```ini\nPROVIDER=spark\nAPI_KEY=\nMODEL=4.0Ultra\n```\n\nOr you can use your `APP_ID` and `API_SECRET`.\n\n```ini\nPROVIDER=spark\nAPP_ID=\nAPP_SECRET=\nMODEL=4.0Ultra\n```\n\n\n## \ud83d\ude80 Usage\n\n### Quick Start\n\n```bash\n# Get a quick answer\nai \"What is the capital of France?\"\n\n# Start an interactive chat session\nai --chat\n\n# Generate and execute shell commands\nai --shell \"Create a backup of my Documents folder\"\n\n# Generate code snippets, default in Python\nai --code \"Write a Python function to sort a list\"\n\n# Analyze code from a file\ncat app.py | ai \"Explain what this code does\"\n\n# Debug with verbose mode\nai --verbose \"Explain quantum computing\"\n```\n\n### Interactive Mode Features\n\n<table>\n<tr>\n<td width=\"50%\">\n\n**Commands**\n\n- `/help|?` - Show help message\n- `/clear` - Clear conversation history\n- `/his` - Show command history\n- `/list` - List saved chats\n- `/save <title>` - Save current chat with title\n- `/load <index>` - Load a saved chat\n- `/del <index>` - Delete a saved chat\n- `/exit` - Exit the application\n- `/mode chat|exec` - Switch modes\n\n**Keyboard Shortcuts**\n\n- `Tab` - Toggle between Chat/Execute modes\n- `Ctrl+C` or `Ctrl+D` - Exit\n- `Ctrl+R` - Search history\n- `\u2191/\u2193` - Navigate through history\n\n</td>\n<td width=\"50%\">\n\n**Chat Mode** (\ud83d\udcac)\n\n- Natural conversations with context\n- Markdown and code formatting\n- Reasoning display for complex queries\n\n**Execute Mode** (\ud83d\ude80)\n\n- Generate shell commands from descriptions\n- Review commands before execution\n- Edit commands before running\n- Safe execution with confirmation\n\n</td>\n</tr>\n</table>\n\n### Chat Persistent\n\nThe `<PROMPT>` parameter in the chat mode will be used as a title to persist the chat content to the file system, with\nthe save directory being a temporary directory, which may vary between machines, and it is determined on the first run.\n\nIf the `<PROMPT>` parameter is not specified when entering `chat` mode, the session will be treated as a temporary\nsession and will not be persisted. Of course, you can also manually call the `/save <title>` command to save during the\nchat.\nWhen you run the same `chat` command again, the previous session will be automatically loaded.\n\n```bash\n$ ai --chat \"meaning of life\"\n```\n\n> !NOTE: Chat mode is not supported when you redirect input to `ai` command.\n>\n> ```bash\n> $ cat error.log | ai --chat \"Explain this error\"\n> ```\n>\n> The above command will be parsed as `ai \"cat error.log | ai \"Explain this error\"`.\n\n**Start a temporary chat session**\n\n```bash\n$ ai --chat\n```\n\n**Start a persistent chat session**\n\n```bash\n$ ai --chat \"check disk usage\"\n```\n\n**Load a saved chat session**\n\n```bash\n$ ai --chat hello\nChat title: hello\n\n \u2588\u2588    \u2588\u2588  \u2588\u2588\u2588\u2588\u2588  \u2588\u2588  \u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588      \u2588\u2588\n  \u2588\u2588  \u2588\u2588  \u2588\u2588   \u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n   \u2588\u2588\u2588\u2588   \u2588\u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n    \u2588\u2588    \u2588\u2588   \u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n    \u2588\u2588    \u2588\u2588   \u2588\u2588 \u2588\u2588  \u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588\n\nWelcome to YAICLI!\nCurrent: Persistent Session: hello\nPress TAB to switch mode\n/clear             : Clear chat history\n/his               : Show chat history\n/list              : List saved chats\n/save <title>      : Save current chat\n/load <index>      : Load a saved chat\n/del <index>       : Delete a saved chat\n/exit|Ctrl+D|Ctrl+C: Exit\n/mode chat|exec    : Switch mode (Case insensitive)\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n \ud83d\udcac > /his\nChat History:\n1 User: hi\n    Assistant:\n    Hello! How can I assist you today?\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n \ud83d\udcac >\n```\n\n### Input Methods\n\n**Direct Input**\n\n```bash\nai \"What is the capital of France?\"\n```\n\n**Piped Input**\n\n```bash\necho \"What is the capital of France?\" | ai\n```\n\n**File Analysis**\n\n```bash\ncat demo.py | ai \"Explain this code\"\n```\n\n**Combined Input**\n\n```bash\ncat error.log | ai \"Why am I getting these errors in my Python app?\"\n```\n\n## \ud83d\udcf1 Examples\n\n### Quick Answer Mode\n\n```bash\n$ ai \"What is the capital of France?\"\nAssistant:\nThe capital of France is Paris.\n```\n\n### Command Generation & Execution\n\n```bash\n$ ai -s 'Check the current directory size'\nAssistant:\ndu -sh .\n\u256d\u2500 Command \u2500\u256e\n\u2502 du -sh .  \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nExecute command? [e]dit, [y]es, [n]o (n): e\nEdit command, press enter to execute:\ndu -sh ./\nOutput:\n109M    ./\n```\n\n### Code Generation\n\nIn code mode, select the language for code generation. If none is specified, Python is the default.\n\nThe `--code` mode outputs plain text, making it easy to copy, paste, or redirect to a file, especially when using the standard model.\n\nWhen using a deep reasoning model, the thinking content is displayed with syntax highlighting. To disable this, use the `--no-show-reasoning` option or set `SHOW_REASONING` to `false` in the configuration.\n\n```bash\n$ ai --code 'Write a fib generator'\ndef fib_generator():\n    a, b = 0, 1\n    while True:\n        yield a\n        a, b = b, a + b\n```\n\n### Chat Mode Example\n\n```bash\n$ ai --chat\nStarting a temporary chat session (will not be saved automatically)\n\n \u2588\u2588    \u2588\u2588  \u2588\u2588\u2588\u2588\u2588  \u2588\u2588  \u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588      \u2588\u2588\n  \u2588\u2588  \u2588\u2588  \u2588\u2588   \u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n   \u2588\u2588\u2588\u2588   \u2588\u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n    \u2588\u2588    \u2588\u2588   \u2588\u2588 \u2588\u2588 \u2588\u2588      \u2588\u2588      \u2588\u2588\n    \u2588\u2588    \u2588\u2588   \u2588\u2588 \u2588\u2588  \u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588\u2588\u2588\u2588\u2588\u2588 \u2588\u2588\n\nWelcome to YAICLI!\nCurrent: Temporary Session (use /save to make persistent)\nPress TAB to switch mode\n/clear             : Clear chat history\n/his               : Show chat history\n/list              : List saved chats\n/save <title>      : Save current chat\n/load <index>      : Load a saved chat\n/del <index>       : Delete a saved chat\n!<command>         : Execute shell command directly (e.g., !ls -al)\n/exit|Ctrl+D|Ctrl+C: Exit\n/mode chat|exec    : Switch mode (Case insensitive)\n\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\n \ud83d\udcac > Tell me about the solar system\n\nAssistant:\nSolar System Overview\n\n \u2022 Central Star: The Sun (99% of system mass, nuclear fusion).\n \u2022 Planets: 8 total.\n    \u2022 Terrestrial (rocky): Mercury, Venus, Earth, Mars.\n    \u2022 Gas Giants: Jupiter, Saturn.\n    \u2022 Ice Giants: Uranus, Neptune.\n \u2022 Moons: Over 200 (e.g., Earth: 1, Jupiter: 95).\n \u2022 Smaller Bodies:\n    \u2022 Asteroids (between Mars/Venus), comets ( icy, distant), * dwarf planets* (Pluto, Ceres).\n \u2022 Oort Cloud: spherical shell of icy objects ~1\u2013100,000\u5929\u6587\u55ae\u4f4d (AU) from Sun).\n \u2022 Heliosphere: Solar wind boundary protecting Earth from cosmic radiation.\n\nKey Fact: Earth is the only confirmed habitable planet.\n\n\ud83d\ude80 > Check the current directory size\nAssistant:\ndu -sh .\n\u256d\u2500 Suggest Command \u2500\u256e\n\u2502 du -sh .          \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nExecute command? [e]dit, [y]es, [n]o (n): e\nEdit command: du -sh ./\n--- Executing ---\n 55M    ./\n--- Finished ---\n\ud83d\ude80 >\n```\n\n### Execute Mode Example\n\n```bash\n$ ai --shell \"Find all PDF files in my Downloads folder\"\nAssistant:\nfind ~/Downloads -type f -name \"*.pdf\"\n\u256d\u2500 Suggest Command \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256e\n\u2502 find ~/Downloads -type f -iname \"*.pdf\" \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nExecute command? [e]dit, [y]es, [n]o (n): y\nOutput:\n\n/Users/username/Downloads/document1.pdf\n/Users/username/Downloads/report.pdf\n...\n```\n\n### Code Mode Example\n\n```bash\n$ ai --code \"write a fib generator\" --model deepseek-r1\n```\n\n![fib code example](artwork/reasoning_code_example.png)\n\n### Function Call\n\nTo use function call, you need to install default functions by `ai --install-functions`.\nAfter that, you can check the functions by `ai --list-functions`.\nYou can also define your own functions by adding them to the config folder in `~/.config/yaicli/functions/` (`C:\\Users\\<user>\\.config\\yaicli\\functions` on Windows).\n\n`--enable-functions` option is corresponds to the configuration key `ENABLE_FUNCTIONS`.\n\n```shell\nai 'check the current dir total size' --enable-functions\nAssistant:\nThinking:\n\n\u258c Okay, the user wants to check the current directory's total size. Hmm, how do I do that in macOS with zsh?\n\u258c I remember that the command to get disk usage is usually 'du'. But wait, the default 'du' might not give the total size of the\n\u258c current directory directly. Let me think. Oh right, if I use 'du -sh' with the current directory, that should give the total size\n\u258c in human-readable format.\n\u258c Wait, but sometimes the -s option summarizes the directory. So 'du -sh .' would calculate the total size of the current directory\n\u258c and its subdirectories. That should work. Let me confirm the syntax. Yeah, 'du -sh .' is the right command here.\n\u258c The user is using zsh, but the 'du' command is standard, so it should be available. I need to execute this shell command. The\n\u258c function provided is execute_shell_command, so I'll call that with the shell command 'du -sh .' as the argument.\n\u258c I should make sure the parameters are correctly formatted. The function requires a shell_command string. Alright, that's all.\n\u258c Let's generate the tool call.\n\n{\"index\":0,\"finish_reason\":\"tool_calls\",\"delta\":{\"role\":\"assistant\",\"content\":null,\"audio\":null,\"tool_calls\":[{\"id\":\"call_202505141526\n36cc3f776ae8f14b56_0\",\"index\":0,\"type\":\"function\",\"function\":{\"name\":\"execute_shell_command\",\"arguments\":\"{\"shell_command\": \"du -sh\n.\"}\",\"outputs\":null},\"code_interpreter\":null,\"retrieval\":null,\"drawing_tool\":null,\"web_browser\":null,\"search_intent\":null,\"search_resu\nlt\":null}],\"tool_call_id\":null,\"attachments\":null,\"metadata\":null}}\n@Function call: execute_shell_command({\"shell_command\": \"du -sh .\"})\n\u256d\u2500 Function output \u2500\u2500\u2500\u2500\u2500\u256e\n\u2502 Exit code: 0, Output: \u2502\n\u2502 156M    .             \u2502\n\u2502                       \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nThinking:\n\n\u258c Okay, the user asked to check the current directory's total size. I used the 'du -sh .' command, which stands for disk usage,\n\u258c summarize, and current directory. The output was \"156M\". So I need to present this in a concise way.\n\u258c First, confirm the command was executed. Then, report the result clearly. Since the user didn't ask for extra details, keep it\n\u258c simple. Just state the total size as 156MB. Maybe mention the command used for transparency. Alright, that should cover it without\n\u258c overcomplicating.\n\nCurrent directory size: 156M (using du -sh .).\n```\n\n### MCP\n\nAdd your MCP config in `~/.config/yaicli/mcp.json` (`C:\\Users\\<user>\\.config\\yaicli\\mcp.json` on Windows.).\n\n`--enable-mcp` option is corresponds to the configuration key `ENABLE_MCP`.\n\nExample:\n\n```shell\nai 'What is the latest exchange rate between the BTC and the US dollar?' --enable-mcp --show-mcp-output\n\nAssistant:\n\n@Mcp call: bing_search({\"query\": \"latest exchange rate between BTC and US dollar\"})\n\u256d\u2500 Mcp output \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256e\n\u2502 [                                                                                                                         \u2502\n\u2502   {                                                                                                                       \u2502\n\u2502     \"id\": \"result_1751024997243_0\",                                                                                       \u2502\n\u2502     \"title\": \"BTC to USD - Bitcoin to US Dollar Conversion - Exchange Rates\",                                             \u2502\n\u2502     \"link\": \"https://www.exchange-rates.org/converter/btc-usd\",                                                           \u2502\n\u2502     \"snippet\": \"11 \u5c0f\u65f6\u4e4b\u524d\u2002\u00b7\u20021 Bitcoin = 107,304 US Dollars as of June 27, 2025 03:00 AM UTC. You can get live exchange  \u2502\n\u2502 rates between Bitcoin and US Dollars using exchange-rates.org, which aggregates \u2026\"                                        \u2502\n\u2502   },                                                                                                                      \u2502\n\u2570\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u256f\nHere are some current exchange rates for Bitcoin (BTC) to US Dollar (USD):                                                   \n\n 1 Exchange-Rates.org:                                                                                                       \n   \u20bf1 Bitcoin = \ud83d\udcb5107,304 US Dollars (as of June 27, 2025, 03:00 AM UTC).                                                    \n   Link                                                                                                                      \n 2 BTC.CurrencyRate.Today:                                                                                                   \n   Live Bitcoin to US Dollars exchange rate.                                                                                 \n   Link                                                                                                                      \n 3 Xe.com:                                                                                                                   \n   Latest conversion rate and information about Bitcoin to US Dollars.                                                       \n   Link                                                                                                                      \n 4 BestExchangeRates.com:                                                                                                    \n   Current BTC to USD market data, including charts and historic rates.                                                      \n   Link                                                                                                                      \n 5 Investing.com:                                                                                                            \n   Bitcoin price analysis and live BTC to USD updates.                                                                       \n   Link                                                                                                                      \n\nFor the most accurate and up-to-date rate, I recommend checking one of these sources directly.                               \n```\n\n![mcp](artwork/mcp_example.png)\n\n\n## \ud83d\udcbb Technical Details\n\n### Architecture\n\nYAICLI is designed with a modular architecture that separates concerns and makes the codebase maintainable:\n\n- **CLI Module**: Handles user interaction and command parsing\n- **API Client**: Manages communication with LLM providers\n- **Config Manager**: Handles layered configuration\n- **History Manager**: Maintains conversation history with LRU functionality\n- **Printer**: Formats and displays responses with rich formatting\n\n### Dependencies\n\n| Library                                                         | Purpose                                            |\n| --------------------------------------------------------------- | -------------------------------------------------- |\n| [Typer](https://typer.tiangolo.com/)                            | Command-line interface with type hints             |\n| [Rich](https://rich.readthedocs.io/)                            | Terminal formatting and beautiful display          |\n| [prompt_toolkit](https://python-prompt-toolkit.readthedocs.io/) | Interactive input with history and auto-completion |\n| [json-repair](https://github.com/mangiucugna/json_repair)       | Repair llm function call arguments                 |\n\n## \ud83d\udc68\u200d\ud83d\udcbb Contributing\n\nContributions are welcome! Here's how you can help:\n\n- **Bug Reports**: Open an issue describing the bug and how to reproduce it\n- **Feature Requests**: Suggest new features or improvements\n- **Code Contributions**: Submit a PR with your changes\n- **Documentation**: Help improve or translate the documentation\n\n## \ud83d\udcc3 License\n\n[Apache License 2.0](LICENSE)\n\n---\n\n<p align=\"center\"><i>YAICLI - Your AI Command Line Interface</i></p>\n",
    "bugtrack_url": null,
    "license": "Apache License\n                                   Version 2.0, January 2004\n                                http://www.apache.org/licenses/\n        \n           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n        \n           1. Definitions.\n        \n              \"License\" shall mean the terms and conditions for use, reproduction,\n              and distribution as defined by Sections 1 through 9 of this document.\n        \n              \"Licensor\" shall mean the copyright owner or entity authorized by\n              the copyright owner that is granting the License.\n        \n              \"Legal Entity\" shall mean the union of the acting entity and all\n              other entities that control, are controlled by, or are under common\n              control with that entity. For the purposes of this definition,\n              \"control\" means (i) the power, direct or indirect, to cause the\n              direction or management of such entity, whether by contract or\n              otherwise, or (ii) ownership of fifty percent (50%) or more of the\n              outstanding shares, or (iii) beneficial ownership of such entity.\n        \n              \"You\" (or \"Your\") shall mean an individual or Legal Entity\n              exercising permissions granted by this License.\n        \n              \"Source\" form shall mean the preferred form for making modifications,\n              including but not limited to software source code, documentation\n              source, and configuration files.\n        \n              \"Object\" form shall mean any form resulting from mechanical\n              transformation or translation of a Source form, including but\n              not limited to compiled object code, generated documentation,\n              and conversions to other media types.\n        \n              \"Work\" shall mean the work of authorship, whether in Source or\n              Object form, made available under the License, as indicated by a\n              copyright notice that is included in or attached to the work\n              (an example is provided in the Appendix below).\n        \n              \"Derivative Works\" shall mean any work, whether in Source or Object\n              form, that is based on (or derived from) the Work and for which the\n              editorial revisions, annotations, elaborations, or other modifications\n              represent, as a whole, an original work of authorship. For the purposes\n              of this License, Derivative Works shall not include works that remain\n              separable from, or merely link (or bind by name) to the interfaces of,\n              the Work and Derivative Works thereof.\n        \n              \"Contribution\" shall mean any work of authorship, including\n              the original version of the Work and any modifications or additions\n              to that Work or Derivative Works thereof, that is intentionally\n              submitted to Licensor for inclusion in the Work by the copyright owner\n              or by an individual or Legal Entity authorized to submit on behalf of\n              the copyright owner. For the purposes of this definition, \"submitted\"\n              means any form of electronic, verbal, or written communication sent\n              to the Licensor or its representatives, including but not limited to\n              communication on electronic mailing lists, source code control systems,\n              and issue tracking systems that are managed by, or on behalf of, the\n              Licensor for the purpose of discussing and improving the Work, but\n              excluding communication that is conspicuously marked or otherwise\n              designated in writing by the copyright owner as \"Not a Contribution.\"\n        \n              \"Contributor\" shall mean Licensor and any individual or Legal Entity\n              on behalf of whom a Contribution has been received by Licensor and\n              subsequently incorporated within the Work.\n        \n           2. Grant of Copyright License. Subject to the terms and conditions of\n              this License, each Contributor hereby grants to You a perpetual,\n              worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n              copyright license to reproduce, prepare Derivative Works of,\n              publicly display, publicly perform, sublicense, and distribute the\n              Work and such Derivative Works in Source or Object form.\n        \n           3. Grant of Patent License. Subject to the terms and conditions of\n              this License, each Contributor hereby grants to You a perpetual,\n              worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n              (except as stated in this section) patent license to make, have made,\n              use, offer to sell, sell, import, and otherwise transfer the Work,\n              where such license applies only to those patent claims licensable\n              by such Contributor that are necessarily infringed by their\n              Contribution(s) alone or by combination of their Contribution(s)\n              with the Work to which such Contribution(s) was submitted. If You\n              institute patent litigation against any entity (including a\n              cross-claim or counterclaim in a lawsuit) alleging that the Work\n              or a Contribution incorporated within the Work constitutes direct\n              or contributory patent infringement, then any patent licenses\n              granted to You under this License for that Work shall terminate\n              as of the date such litigation is filed.\n        \n           4. Redistribution. You may reproduce and distribute copies of the\n              Work or Derivative Works thereof in any medium, with or without\n              modifications, and in Source or Object form, provided that You\n              meet the following conditions:\n        \n              (a) You must give any other recipients of the Work or\n                  Derivative Works a copy of this License; and\n        \n              (b) You must cause any modified files to carry prominent notices\n                  stating that You changed the files; and\n        \n              (c) You must retain, in the Source form of any Derivative Works\n                  that You distribute, all copyright, patent, trademark, and\n                  attribution notices from the Source form of the Work,\n                  excluding those notices that do not pertain to any part of\n                  the Derivative Works; and\n        \n              (d) If the Work includes a \"NOTICE\" text file as part of its\n                  distribution, then any Derivative Works that You distribute must\n                  include a readable copy of the attribution notices contained\n                  within such NOTICE file, excluding those notices that do not\n                  pertain to any part of the Derivative Works, in at least one\n                  of the following places: within a NOTICE text file distributed\n                  as part of the Derivative Works; within the Source form or\n                  documentation, if provided along with the Derivative Works; or,\n                  within a display generated by the Derivative Works, if and\n                  wherever such third-party notices normally appear. The contents\n                  of the NOTICE file are for informational purposes only and\n                  do not modify the License. You may add Your own attribution\n                  notices within Derivative Works that You distribute, alongside\n                  or as an addendum to the NOTICE text from the Work, provided\n                  that such additional attribution notices cannot be construed\n                  as modifying the License.\n        \n              You may add Your own copyright statement to Your modifications and\n              may provide additional or different license terms and conditions\n              for use, reproduction, or distribution of Your modifications, or\n              for any such Derivative Works as a whole, provided Your use,\n              reproduction, and distribution of the Work otherwise complies with\n              the conditions stated in this License.\n        \n           5. Submission of Contributions. Unless You explicitly state otherwise,\n              any Contribution intentionally submitted for inclusion in the Work\n              by You to the Licensor shall be under the terms and conditions of\n              this License, without any additional terms or conditions.\n              Notwithstanding the above, nothing herein shall supersede or modify\n              the terms of any separate license agreement you may have executed\n              with Licensor regarding such Contributions.\n        \n           6. Trademarks. This License does not grant permission to use the trade\n              names, trademarks, service marks, or product names of the Licensor,\n              except as required for reasonable and customary use in describing the\n              origin of the Work and reproducing the content of the NOTICE file.\n        \n           7. Disclaimer of Warranty. Unless required by applicable law or\n              agreed to in writing, Licensor provides the Work (and each\n              Contributor provides its Contributions) on an \"AS IS\" BASIS,\n              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n              implied, including, without limitation, any warranties or conditions\n              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n              PARTICULAR PURPOSE. You are solely responsible for determining the\n              appropriateness of using or redistributing the Work and assume any\n              risks associated with Your exercise of permissions under this License.\n        \n           8. Limitation of Liability. In no event and under no legal theory,\n              whether in tort (including negligence), contract, or otherwise,\n              unless required by applicable law (such as deliberate and grossly\n              negligent acts) or agreed to in writing, shall any Contributor be\n              liable to You for damages, including any direct, indirect, special,\n              incidental, or consequential damages of any character arising as a\n              result of this License or out of the use or inability to use the\n              Work (including but not limited to damages for loss of goodwill,\n              work stoppage, computer failure or malfunction, or any and all\n              other commercial damages or losses), even if such Contributor\n              has been advised of the possibility of such damages.\n        \n           9. Accepting Warranty or Additional Liability. While redistributing\n              the Work or Derivative Works thereof, You may choose to offer,\n              and charge a fee for, acceptance of support, warranty, indemnity,\n              or other liability obligations and/or rights consistent with this\n              License. However, in accepting such obligations, You may act only\n              on Your own behalf and on Your sole responsibility, not on behalf\n              of any other Contributor, and only if You agree to indemnify,\n              defend, and hold each Contributor harmless for any liability\n              incurred by, or claims asserted against, such Contributor by reason\n              of your accepting any such warranty or additional liability.\n        \n           END OF TERMS AND CONDITIONS\n        \n           APPENDIX: How to apply the Apache License to your work.\n        \n              To apply the Apache License to your work, attach the following\n              boilerplate notice, with the fields enclosed by brackets \"[]\"\n              replaced with your own identifying information. (Don't include\n              the brackets!)  The text should be enclosed in the appropriate\n              comment syntax for the file format. We also recommend that a\n              file or class name and description of purpose be included on the\n              same \"printed page\" as the copyright notice for easier\n              identification within third-party archives.\n        \n           Copyright [yyyy] [name of copyright owner]\n        \n           Licensed under the Apache License, Version 2.0 (the \"License\");\n           you may not use this file except in compliance with the License.\n           You may obtain a copy of the License at\n        \n               http://www.apache.org/licenses/LICENSE-2.0\n        \n           Unless required by applicable law or agreed to in writing, software\n           distributed under the License is distributed on an \"AS IS\" BASIS,\n           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n           See the License for the specific language governing permissions and\n           limitations under the License.",
    "summary": "A simple CLI tool to interact with LLM",
    "version": "0.8.10",
    "project_urls": {
        "Documentation": "https://github.com/belingud/yaicli",
        "Homepage": "https://github.com/belingud/yaicli",
        "Repository": "https://github.com/belingud/yaicli"
    },
    "split_keywords": [
        "ai",
        " ai-assistant",
        " ai-chat",
        " ai-interaction",
        " anthropic",
        " chatglm",
        " chatgpt",
        " claude",
        " cli",
        " cohere",
        " command-line",
        " completion",
        " console-application",
        " conversation",
        " deepseek",
        " gemini",
        " gpt",
        " groq",
        " huggingface",
        " inference",
        " interactive",
        " language-model",
        " llm",
        " llms",
        " mistral",
        " modelscope",
        " nlp",
        " ollama",
        " openai",
        " prompt",
        " python-tool",
        " sambanova",
        " shell-integration",
        " siliconflow",
        " terminal",
        " terminal-interface",
        " text-generation",
        " vertexai",
        " xai"
    ],
    "urls": [
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "3829b27d4ffc8242a03b7ea7840be06841043aaf978a0248ee0d3548df4e716e",
                "md5": "9059288f9e01681139f6ead77e829b01",
                "sha256": "767d52d83e93d87b632dcc29eaf494286f9ccb8580bb816374797adadecbf3b9"
            },
            "downloads": -1,
            "filename": "yaicli-0.8.10-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "9059288f9e01681139f6ead77e829b01",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.10",
            "size": 104222,
            "upload_time": "2025-07-24T05:37:02",
            "upload_time_iso_8601": "2025-07-24T05:37:02.862123Z",
            "url": "https://files.pythonhosted.org/packages/38/29/b27d4ffc8242a03b7ea7840be06841043aaf978a0248ee0d3548df4e716e/yaicli-0.8.10-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "0d9f64a3ea13f320ecd158102c4b02ea668111a39f4530bf29f25567e22bcded",
                "md5": "7c2bc3dfc7046b7b95f2c44199b5903f",
                "sha256": "fbac5e40251e4449821ed5d3bef7dd88fb0606eb65eeca585d284a4076f802da"
            },
            "downloads": -1,
            "filename": "yaicli-0.8.10.tar.gz",
            "has_sig": false,
            "md5_digest": "7c2bc3dfc7046b7b95f2c44199b5903f",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.10",
            "size": 84401,
            "upload_time": "2025-07-24T05:37:04",
            "upload_time_iso_8601": "2025-07-24T05:37:04.229425Z",
            "url": "https://files.pythonhosted.org/packages/0d/9f/64a3ea13f320ecd158102c4b02ea668111a39f4530bf29f25567e22bcded/yaicli-0.8.10.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2025-07-24 05:37:04",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "belingud",
    "github_project": "yaicli",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "tox": true,
    "lcname": "yaicli"
}