| Name | Version | Summary | date |
| aa-kit |
0.3.0 |
The Universal AI Agent Framework for the MCP Era |
2025-07-10 20:28:52 |
| hacs-anthropic |
0.3.1 |
Anthropic Claude integration for HACS (Healthcare Agent Communication Standard) |
2025-07-10 14:43:09 |
| wraipperz |
0.1.41 |
Simple wrappers for various AI APIs including LLMs, ASR, and TTS |
2025-07-09 07:53:11 |
| mseep-mcp-kql-server |
2.0.1 |
AI-Powered MCP server for KQL query execution with intelligent schema memory and context assistance |
2025-07-09 00:52:54 |
| llmcosts |
0.2.5 |
A generic, provider-agnostic SDK wrapper that intercepts LLM API responses and extracts usage information for cost tracking with structured payload formatting. |
2025-07-08 19:40:18 |
| arc-runtime |
0.1.2 |
Lightweight Python interceptor that prevents AI agent failures in real-time |
2025-07-08 16:01:46 |
| geekbot-mcp |
0.1.3 |
Model Context Protocol (MCP) server integrating Geekbot data and tools to Claude AI |
2025-04-07 21:29:54 |
| mirascope |
1.22.1 |
LLM abstractions that aren't obstructions |
2025-03-22 07:03:10 |
| smartllm |
0.0.6 |
A unified interface for interacting with multiple Large Language Model providers |
2025-03-21 20:24:03 |
| parllama |
0.3.18 |
Terminal UI for Ollama and other LLM providers |
2025-02-19 17:16:44 |
| mockllm |
0.1.0 |
A mock server that mimics OpenAI and Anthropic API formats for testing |
2025-02-14 16:59:46 |
| smolllm |
0.1.8 |
A minimal Python library for interacting with various LLM providers |
2025-02-14 03:15:59 |
| congruent |
0.0.8 |
A CLI for interacting with LLMs, with tracking, validation, integrations, and UI. |
2025-02-12 10:50:00 |
| hyjinx |
1.0.11 |
A minimal Hy utility library, using mostly the standard libraries. |
2025-02-05 12:09:47 |
| reasoning |
0.1.0 |
A reasoning framework for all LLMs |
2025-02-04 03:00:03 |
| pyllms |
0.7.1 |
Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Mistral, OpenRouter, Reka, Groq, Together, Ollama, AI21, Cohere, Aleph-Alpha, HuggingfaceHub), with a built-in model performance benchmark. |
2025-01-29 02:33:40 |
| long2short |
0.1.3 |
A flexible text summarization library to summarize long documents supporting multiple LLM providers |
2025-01-23 11:13:46 |
| gpt-command-line |
0.3.2 |
Command-line interface for ChatGPT and Claude |
2025-01-23 03:52:24 |
| blnk-chat |
0.2.0 |
A powerful terminal-based chat application for seamless interaction with multiple AI providers |
2025-01-16 22:55:00 |
| based-cli |
0.0.7 |
A powerful CLI tool for interacting with various AI models |
2025-01-15 04:39:54 |