unisonai


Nameunisonai JSON
Version 0.8 PyPI version JSON
download
home_pageNone
SummaryUnisonAI Multi-Agent Framework provides a flexible, light-weight experience and extensible environment for creating and coordinating multiple AI agents.
upload_time2025-07-22 13:31:25
maintainerNone
docs_urlNone
authorE5Anant (Anant Sharma)
requires_pythonNone
licenseNone
keywords agents unisonai unisonai multi-agent clan python light-weight agent-framework framework ai ai tools ai agents llms open-source a2a agent to agent
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            
# ![UnisonAI Banner](https://github.com/UnisonAIInc/UnisonAI/blob/main/assets/UnisonAI_Banner.jpg)



# UnisonAI



[![GitHub stars](https://img.shields.io/github/stars/UnisonAIInc/UnisonAI?style=social)](https://github.com/UnisonAIInc/UnisonAI/stargazers)

[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)

[![Python](https://img.shields.io/badge/Python-3.10%20--%203.12-blue)](https://pypi.org/project/unisonai/)

[![LLM Support](https://img.shields.io/badge/LLM%20Support-OpenAI%2C%20Anthropic%2C%20Gemini-orange)](https://pypi.org/project/unisonai/)

[![Architecture](https://img.shields.io/badge/Architecture-Single%20Agent%20%2F%20Clan%20A2A-purple)](https://pypi.org/project/unisonai/)



---



UnisonAI is a flexible Python framework to build and manage multiple AI agentsβ€”either solo or in clans. Each agent is powered by the LLM of your choice, with agent-to-agent (A2A) communication capabilities.



## ✨ Key Features



* πŸ”— **Multi-LLM Support:** OpenAI, Grok, Gemini, Cohere, Anthropic, and more

* 🧩 **Modular & Extensible:** Add your own tools, logic, and models

* πŸ€– **Single or Multi-Agent:** Solo agents or collaborative Clan agents

* ⛨️ **Error Handling:** Built-in retries and format repairs

* πŸ“ƒ **Clear Docs & Examples:** Easy to start and extend

* ⚑ **Production Ready:** Ideal for real-world automation & chatbots



---



## πŸš€ Installation



```bash

pip install unisonai

```



> Requires Python >=3.10 and <3.13



---



## 🧠 Core Concepts



**Single\_Agent**

Run focused tasks with isolated agents using any LLM and tools.



**Agent (for Clans)**

A specialized agent that communicates and collaborates with others.



**Clan**

A group of agents working together with a manager and a shared goal.



**Tool System**

Add your own pluggable tools with parameters and logic.



---



## πŸ”§ Usage Example (Single Agent)



```python

from unisonai import Single_Agent

from unisonai.llms import Gemini

from unisonai.tools.websearch import WebSearchTool

from unisonai import config



config.set_api_key("gemini", "your-api-key")



agent = Single_Agent(

  llm=Gemini(model="gemini-2.0-flash"),

  identity="Web Explorer",

  description="Agent to fetch stock prices",

  tools=[WebSearchTool],

  history_folder="history",

  output_file="output.txt"

)



agent.unleash(task="Get the current price of Apple stocks")

```



---



## πŸ—Ί Usage Example (Clan Agent)



```python

from unisonai import Agent, Clan

from unisonai.llms import Gemini

from unisonai.tools.websearch import WebSearchTool

from unisonai import config



config.set_api_key("gemini", "your-api-key")



planner = Agent(...)  # Define your clan leader agent



web_agent = Agent(...)

time_agent = Agent(...)



clan = Clan(

  clan_name="Travel Experts",

  manager=planner,

  members=[web_agent, time_agent],

  shared_instruction="Plan a 7-day budget trip in India",

  goal="Create an itinerary under 10,000 INR",

  history_folder="trip_history",

  output_file="trip_plan.txt"

)



clan.unleash()

```



---



## πŸ”‘ API Key Setup



```python

from unisonai import config

config.set_api_key("gemini", "your-gemini-key")

config.set_api_key("openai", "your-openai-key")

```



You can also use environment variables:



```bash

export GEMINI_API_KEY="your-key"

```



---



## ❓ FAQ



**What is UnisonAI?**

A multi-agent AI framework using your favorite LLMs.



**Why Clans?**

Break tasks into parts and assign agents to solve each collaboratively.



**Can I use custom models/tools?**

Yes! Just extend the `BaseLLM` or `BaseTool` classes.



**Where are logs stored?**

In the folder you define using `history_folder`.



**What can I build?**

Chatbots, planners, assistants, automation systems, and more.



---



## πŸ‘₯ Contributors & License



* **Lead Developer:** [@E5Anant](https://github.com/E5Anant)

* **Contributors:** [@AnonymousCoderArtist](https://github.com/AnonymousCoderArtist), [@OEvortex](https://github.com/OEvortex)



**License:** [Apache 2.0](https://github.com/UnisonAIInc/UnisonAI/blob/main/LICENSE)



GitHub: [https://github.com/UnisonAIInc/UnisonAI](https://github.com/UnisonAIInc/UnisonAI)



---



**UnisonAI β€” Orchestrate the Future of Multi-Agent AI**


            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "unisonai",
    "maintainer": null,
    "docs_url": null,
    "requires_python": null,
    "maintainer_email": null,
    "keywords": "agents, unisonai, unisonAI, multi-agent, clan, python, light-weight, agent-framework, framework, ai, ai tools, ai agents, llms, open-source, a2a, agent to agent",
    "author": "E5Anant (Anant Sharma)",
    "author_email": "e5anant2011@gmail.com",
    "download_url": "https://files.pythonhosted.org/packages/26/f9/72b1796977aea90cebf9a1d68042f19a348260e8da4fdf752790fa190052/unisonai-0.8.tar.gz",
    "platform": null,
    "description": "\r\n# ![UnisonAI Banner](https://github.com/UnisonAIInc/UnisonAI/blob/main/assets/UnisonAI_Banner.jpg)\r\r\n\r\r\n# UnisonAI\r\r\n\r\r\n[![GitHub stars](https://img.shields.io/github/stars/UnisonAIInc/UnisonAI?style=social)](https://github.com/UnisonAIInc/UnisonAI/stargazers)\r\r\n[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)\r\r\n[![Python](https://img.shields.io/badge/Python-3.10%20--%203.12-blue)](https://pypi.org/project/unisonai/)\r\r\n[![LLM Support](https://img.shields.io/badge/LLM%20Support-OpenAI%2C%20Anthropic%2C%20Gemini-orange)](https://pypi.org/project/unisonai/)\r\r\n[![Architecture](https://img.shields.io/badge/Architecture-Single%20Agent%20%2F%20Clan%20A2A-purple)](https://pypi.org/project/unisonai/)\r\r\n\r\r\n---\r\r\n\r\r\nUnisonAI is a flexible Python framework to build and manage multiple AI agents\u2014either solo or in clans. Each agent is powered by the LLM of your choice, with agent-to-agent (A2A) communication capabilities.\r\r\n\r\r\n## \u2728 Key Features\r\r\n\r\r\n* \ud83d\udd17 **Multi-LLM Support:** OpenAI, Grok, Gemini, Cohere, Anthropic, and more\r\r\n* \ud83e\udde9 **Modular & Extensible:** Add your own tools, logic, and models\r\r\n* \ud83e\udd16 **Single or Multi-Agent:** Solo agents or collaborative Clan agents\r\r\n* \u26e8\ufe0f **Error Handling:** Built-in retries and format repairs\r\r\n* \ud83d\udcc3 **Clear Docs & Examples:** Easy to start and extend\r\r\n* \u26a1 **Production Ready:** Ideal for real-world automation & chatbots\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83d\ude80 Installation\r\r\n\r\r\n```bash\r\r\npip install unisonai\r\r\n```\r\r\n\r\r\n> Requires Python >=3.10 and <3.13\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83e\udde0 Core Concepts\r\r\n\r\r\n**Single\\_Agent**\r\r\nRun focused tasks with isolated agents using any LLM and tools.\r\r\n\r\r\n**Agent (for Clans)**\r\r\nA specialized agent that communicates and collaborates with others.\r\r\n\r\r\n**Clan**\r\r\nA group of agents working together with a manager and a shared goal.\r\r\n\r\r\n**Tool System**\r\r\nAdd your own pluggable tools with parameters and logic.\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83d\udd27 Usage Example (Single Agent)\r\r\n\r\r\n```python\r\r\nfrom unisonai import Single_Agent\r\r\nfrom unisonai.llms import Gemini\r\r\nfrom unisonai.tools.websearch import WebSearchTool\r\r\nfrom unisonai import config\r\r\n\r\r\nconfig.set_api_key(\"gemini\", \"your-api-key\")\r\r\n\r\r\nagent = Single_Agent(\r\r\n  llm=Gemini(model=\"gemini-2.0-flash\"),\r\r\n  identity=\"Web Explorer\",\r\r\n  description=\"Agent to fetch stock prices\",\r\r\n  tools=[WebSearchTool],\r\r\n  history_folder=\"history\",\r\r\n  output_file=\"output.txt\"\r\r\n)\r\r\n\r\r\nagent.unleash(task=\"Get the current price of Apple stocks\")\r\r\n```\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83d\uddfa Usage Example (Clan Agent)\r\r\n\r\r\n```python\r\r\nfrom unisonai import Agent, Clan\r\r\nfrom unisonai.llms import Gemini\r\r\nfrom unisonai.tools.websearch import WebSearchTool\r\r\nfrom unisonai import config\r\r\n\r\r\nconfig.set_api_key(\"gemini\", \"your-api-key\")\r\r\n\r\r\nplanner = Agent(...)  # Define your clan leader agent\r\r\n\r\r\nweb_agent = Agent(...)\r\r\ntime_agent = Agent(...)\r\r\n\r\r\nclan = Clan(\r\r\n  clan_name=\"Travel Experts\",\r\r\n  manager=planner,\r\r\n  members=[web_agent, time_agent],\r\r\n  shared_instruction=\"Plan a 7-day budget trip in India\",\r\r\n  goal=\"Create an itinerary under 10,000 INR\",\r\r\n  history_folder=\"trip_history\",\r\r\n  output_file=\"trip_plan.txt\"\r\r\n)\r\r\n\r\r\nclan.unleash()\r\r\n```\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83d\udd11 API Key Setup\r\r\n\r\r\n```python\r\r\nfrom unisonai import config\r\r\nconfig.set_api_key(\"gemini\", \"your-gemini-key\")\r\r\nconfig.set_api_key(\"openai\", \"your-openai-key\")\r\r\n```\r\r\n\r\r\nYou can also use environment variables:\r\r\n\r\r\n```bash\r\r\nexport GEMINI_API_KEY=\"your-key\"\r\r\n```\r\r\n\r\r\n---\r\r\n\r\r\n## \u2753 FAQ\r\r\n\r\r\n**What is UnisonAI?**\r\r\nA multi-agent AI framework using your favorite LLMs.\r\r\n\r\r\n**Why Clans?**\r\r\nBreak tasks into parts and assign agents to solve each collaboratively.\r\r\n\r\r\n**Can I use custom models/tools?**\r\r\nYes! Just extend the `BaseLLM` or `BaseTool` classes.\r\r\n\r\r\n**Where are logs stored?**\r\r\nIn the folder you define using `history_folder`.\r\r\n\r\r\n**What can I build?**\r\r\nChatbots, planners, assistants, automation systems, and more.\r\r\n\r\r\n---\r\r\n\r\r\n## \ud83d\udc65 Contributors & License\r\r\n\r\r\n* **Lead Developer:** [@E5Anant](https://github.com/E5Anant)\r\r\n* **Contributors:** [@AnonymousCoderArtist](https://github.com/AnonymousCoderArtist), [@OEvortex](https://github.com/OEvortex)\r\r\n\r\r\n**License:** [Apache 2.0](https://github.com/UnisonAIInc/UnisonAI/blob/main/LICENSE)\r\r\n\r\r\nGitHub: [https://github.com/UnisonAIInc/UnisonAI](https://github.com/UnisonAIInc/UnisonAI)\r\r\n\r\r\n---\r\r\n\r\r\n**UnisonAI \u2014 Orchestrate the Future of Multi-Agent AI**\r\r\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "UnisonAI Multi-Agent Framework provides a flexible, light-weight experience and extensible environment for creating and coordinating multiple AI agents.",
    "version": "0.8",
    "project_urls": null,
    "split_keywords": [
        "agents",
        " unisonai",
        " unisonai",
        " multi-agent",
        " clan",
        " python",
        " light-weight",
        " agent-framework",
        " framework",
        " ai",
        " ai tools",
        " ai agents",
        " llms",
        " open-source",
        " a2a",
        " agent to agent"
    ],
    "urls": [
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "fc54d2f9232474390271346037bdb030672b991695d330e230756d029391cbd8",
                "md5": "738d0b62db512a1abfeb52f2d3195be7",
                "sha256": "5c0967c202430564a96cb6ce9a70ff83abaa7ca04045affd75f6cee5dcb93b42"
            },
            "downloads": -1,
            "filename": "unisonai-0.8-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "738d0b62db512a1abfeb52f2d3195be7",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 60425,
            "upload_time": "2025-07-22T13:31:22",
            "upload_time_iso_8601": "2025-07-22T13:31:22.776347Z",
            "url": "https://files.pythonhosted.org/packages/fc/54/d2f9232474390271346037bdb030672b991695d330e230756d029391cbd8/unisonai-0.8-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "26f972b1796977aea90cebf9a1d68042f19a348260e8da4fdf752790fa190052",
                "md5": "607cf54fe1495db029850b843172cc74",
                "sha256": "980d98814ddafb4af09e9623ed6c9219ff3c565d2329cfa3dd90612d80d01b3e"
            },
            "downloads": -1,
            "filename": "unisonai-0.8.tar.gz",
            "has_sig": false,
            "md5_digest": "607cf54fe1495db029850b843172cc74",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 52065,
            "upload_time": "2025-07-22T13:31:25",
            "upload_time_iso_8601": "2025-07-22T13:31:25.392943Z",
            "url": "https://files.pythonhosted.org/packages/26/f9/72b1796977aea90cebf9a1d68042f19a348260e8da4fdf752790fa190052/unisonai-0.8.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2025-07-22 13:31:25",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "unisonai"
}
        
Elapsed time: 1.98660s