Python agents

DeepAgent 기반 Research(연구) Multi Agent System 구축 - Context Engineering

AI tools & automation for creating short viral videos using VEO3 model

This project is everything Chat-GPT should be for developers! An advanced AI-driven coding companion tailored for developers. Seamlessly bridging the gap between traditional coding and AI capabilities, we offer real-time chat interactions, on-demand agent functions, and intuitive code management. Feedback welcome!

LLM driven natural language to generate summaries, bibliography lists, download PDF reports autonomously and extract and visualise open domain data (curently uses GPlates, Macrostrat and Mindat).

⚡ Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x (43 tools) & 3.0+ (45+ tools).

Semantic memory system with knowledge graph, spreading activation, embedding-based recall, autonomous dream consolidation, and C++ LSTM+kNN pattern learning for any /MCP and the Hermes Agent.

用 ~5000 行 Python 还原 CC 的核心 Agent Runtime。

Vibe Coding Framework - Full SaaS Development Team from A-Z with Brain, Self Improvement, Auto Development

[NeurIPS'25] ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions

An experimental Retrieval-Augmented Generation (RAG) system specialised in ingesting MediaWiki sites via their API and providing an OpenAI API interface to interact with them.

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations. Local tiers first; LLM judge only when uncertain.

多Agent量化交易与投资决策系统 | 6-Agent并行+辩论+风控 | Python/Java/Go三语言实现 | 配套面试八股文+STAR法+简历模板 | 从零到面试全攻略

A Claude Code skill that builds a persistent context system (atlas) for any git repository — directory trees, entrypoints, architecture docs, and agent on-ramp for fast LLM onboarding.

Idea-Catalyst is a metacognition-driven framework for helping humans and LLMs boost their creativity during the scientific brainstorming process.

Home Assistant integration for monitoring Claude (Anthropic) subscription usage in Home Assistant. Search for "Claude Usage" in HACS.

Turn any website into clean, LLM-ready data. Open-source web crawler with stealth mode, distributed crawling, real-time WebSocket progress & Markdown output. Power your AI apps with GcrawlAI.

The AI assistant for knowledge workers — a local-first personal-agent runtime built on Claude Code and Obsidian.

PurrCat Agent

WeChatBot 基于ItChat-UOS的 个人微信号OpenAI机器人

AI agent skills and MCP integration for Credyt — real-time usage-based billing for AI products. Works with Claude Code, Cursor, Codex, and Copilot. Add wallets, credits, usage metering, and a customer Billing Portal to any project with a single prompt.

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

AgentCat is an analytics platform for MCP server owners 🐱.

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

闲鱼 Agent 化购物助理。LLM 可直接调用工具完成搜索、订阅管理、收藏及任意复杂页面操作；支持关键词订阅轮询、上新降价检测、LLM 推荐排序与 WebUI 管理。本地或远程部署均可，远程模式下 AstrBot 宿主机无需 Playwright。

Benchmark suite for evaluating agent and LLM memory systems

基于 LangGraph 和 FastAPI 的电商 AI Agent 框架。从 RAG 知识库到复杂的退货业务流的智能客服系统。

本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。

CubePi — An async-first Python agent kernel inspired by Pi, built for coding agents, tools, and continuous sessions.

gradio region:us

gguf code codeqwen chat qwen qwen-coder

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

Always-current official Claude docs inside Claude Code. A 3 MB metadata plugin: live on-demand fetching from Anthropic's servers, zero content redistributed. Auto-discovery skill, instant search, interactive HTML courses, and doc changelog reports.

一个面向 Web 版桌面 安全测试的 AI Agent 平台，集成侦察、分析、规划、工具调用与反馈学习，实现自主完成渗透测试工作流An AI Agent platform for web-based security testing, integrating reconnaissance, analysis, planning, tool orchestration, and feedback-driven learning to autonomously execute penetration testing workflows.

Measured, monotonic, lossless input savings for Codex.

把一张插图渲染为连续落笔、逐步上色、最后停留展示的流式笔迹白板手绘动画，并导出 H.264 MP4。支持单图与批量队列渲染。

多智能体小说写作框架 | Multi-agent novel-writing framework — 每个角色都有自己的脑子,每一章都有质量门禁

Open Swiss legal corpus + MCP server: 1M+ court decisions (1875–today), 21k laws, 10M-edge citation graph, 42 MCP tools. CC0 data, MIT code. Live at mcp.opencaselaw.ch

🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测的 AI Agent 运行时。

An autonomous Kubernetes SRE agent. It monitors cluster health, diagnoses issues, and applies fixes — with human approval required before any write operation.

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain.

Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

Zero downtime embedding upgrades

标书匠 BidCraft · 对话式标书编制系统：AI 智能编制技术标，支持招标文件解析、标段选择、标书编写、知识库提炼与学习对话式改稿。LLM-Wiki 路线，基于LangGraph实现。Open-source AI agent for construction tender & bid documents.

A Twitter bot that reads the tweets of a given username and analyzes the user's personality using AI.

Turn any document into ready-to-use AI image prompts.

Easy "1-line" calling of all LLMs from OpenAI, MS Azure, AWS Bedrock, GCP Vertex, and Ollama

VSCode coding companion for software teams 🦆 Turn your team insights into a portable plug-and-play context for code generation. Alternative to GitHub Copilot & OpenAI GPT powered by OSS LLMs (Phi 3, Llama 3, CodeQwen, Mistral, etc.), made with ❤️ using FastAPI & Ollama.

A supervisor agent for open agent platform

A lightweight Python package for managing multi-agent orchestration. Easily define agents with custom instructions, tools, containers, and models, and orchestrate their interactions seamlessly. Perfect for building modular, collaborative AI systems.

MCP server connecting AI agents to ITASCA PFC — run DEM simulations through natural conversation

Analyze your code locally using a GPT LLM.

ChatGPT wrapper in your TTY

Multimodal Instruction Tuning for Llama 3

ChatGPT Telegram bot

Translate text by google, bing, youdaozhiyun, haici, stardict, openai, large language model of local machine, etc at same time from CLI, GUI (GNU/Linux, Android, macOS and Windows), REPL, python, shell and vim.

Autofill your pull request descriptions with the power of OpenAI

Turn PostgreSQL into your search engine in a Pythonic way.

Event-Driven Autonomous Agents. create alerts in the form of "When X happens, then do Y". In this initial version, we are only supporting email alerts in the form of "When X happens, send me an email report".

Financial Agentic AI redefines financial analysis by integrating cutting-edge AI with real-time web search capabilities. This multi-agent system brings together financial insights and web intelligence to deliver precise, actionable, and up-to-date stock market information, all tailored to your needs.

An advanced distributed knowledge fabric for intelligent document processing, featuring multi-document agents, optimized query handling, and semantic understanding.

[NeurIPS'25] ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding

This repo is the implementation of paper ''SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning''.

🦆 DUCK-E: The Duck That Talks Back - An AI-powered voice assistant that revolutionizes rubber duck debugging by actively engaging in your debugging process. Built with OpenAI Realtime API, FastAPI, and AutoGen framework for intelligent, real-time voice conversations about your code.

86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.

A toolkit for developing AI agents, including agent-debugger: Terminal debugger for LangGraph & LangChain agents. Debug LLM agents with state inspection, tool calls, semantic breakpoints, and Python program stepping in one Textual UI.

WeChat chatbot built on LangChain + FastAPI + itchat · 基于 LangChain + FastAPI + itchat 的微信聊天机器人，灵感来自 chatgpt-on-wechat

🦜 🔗 Query and obtain data from Markdown documents with LangChain's RAG system

Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams

Nexus - The Agentic Framework created by Talus

LLM router + minimal agent framework in one. Call any LLM API with OpenAI format. Unified billing, tools, retries, fallback, logging. Build agents and AI apps in pure Python. Full control. Zero magic.

Unified interface for interacting with various LLMs hundreds of models, caching, fallback mechanisms, and enhanced reliability.

Open source alternative of ChatGPT-4o, FREE!

Use this to create your own AI Agent: Includes OpenAI Docs / Cursor Rules / and Persistent Threads.

Test framework for libraries and agents.

A general framework for developing agent-based models in Python.

Squrve is a lightweight yet powerful framework for translating natural language into SQL over complex databases.

Effortlessly secure your AI agents and AI-powered workflows — from prototype to production. Get easy-to-use identity, credential, and access management built for fast-moving AI developers.

Official Code for "A Set of Control Points Conditioned Pedestrian Trajectory Prediction (AAAI 2023)"

An agent fine tuned on the injective trading framework and docs

Search, preview, and download open-source AI agent skills for Claude Code, Codex, ChatGPT, and MCP workflows.

A Reinforcement Learning (RL) simulation environment built for training and evaluating defensive and offensive autonomous models on simulated and emulated networks, with a focus on modularity and configurability.

This repo is a beginner's guide to using Chroma. It covers all the major features including adding data, querying collections, updating and deleting data, and using different embedding functions. Each topic has its own dedicated folder with a detailed README and corresponding Python scripts for a practical understanding.

Multi Agent Traffic Scenario Gym: A scenario-based training and evaluation framework for CARLA.

AI-powered Python library that converts any document (PDF, Word, Excel, PowerPoint, HTML) to clean Markdown while preserving complex tables and layouts using AI-Powered OCR technology.

A minimal implementation of GraphRAG, designed to quickly prototype whether you're able to get good sense-making out of a large dataset with creation of a knowledge graph.

微软开源多Agent智能体协作框架AutoGen全新改版核心概念介绍及相关案例测试

layer that lets you connect any agent, any tool, any api together.

Recursive AI System

Python SDK for interacting with the Moorcheh Semantic Search API v1. Moorcheh provides ultra-fast, highly accurate vector similarity search and analysis capabilities based on information-theoretic principles.

Code and data for the paper: On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents

[NAACL 2025] AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction.

OneKey Agent Gateway access to Commercial APIs, Skills, MCPs Build once and Ship 10× faster. For devs & builders, A unified API registry to serve and distribute across all agent formats—CLI, REST, MCP, and Skills—eliminating multiple builds. Access 30+ categories like search, image, finance, and 3D Rendering, register, and monetize APIs 10× faster

Local Retrieval-Augmented Generation (RAG) plugin for Claude Code that combines Chroma db vector embeddings with intelligent info retrieval with Multi-Agent Framework (MAF) orchestration for context-aware development assistance. Uses Open Source / Free frameworks. Implements bridge to Claude Code CLI so no token use. And it's easy to setup.

图像生成插件，支持生图和改图，可以自动获取头像作为参考等。

PyTorch implementation of "SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognition"

Multi-agent Claude Code skill for building apps and stuff

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration