Python agents

An implementation of iterative deep research using the OpenAI Agents SDK

Agent skills for interface design, React, React Native, and software security.

CodeGate: Security, Workspaces and Multiplexing for AI Agentic Frameworks

A simple OpenAI Gym environment for single and multi-agent reinforcement learning

transformers safetensors qwen text-generation custom_code zh

Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js

An LLM-driven data analyst that works in a persistent Python kernel. Web app, Docker-isolated execution, your own model keys. Full support for open weights models via provider or local.

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds

A chatbot/GraphRAG framework that creates multi-llm-agents from social platform user comments and let them debate on specific topics.

🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.

open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.

更适配中文用户的轻量开源AI Agent | 国产大模型Coding plan支持 | 兼容OpenClaw Skills生态| 已接入微信ClawBot/微博龙虾/飞书/钉钉/QQ/小智AI/Telegram/deepseek-v4。

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

Hierarchical agent loops with recursive self-organization.

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

Open-source VMs-as-a-service

This demo shows a multi-turn conversation with an AI agent running inside a Temporal workflow.

Canonical source and governance toolkit for Zhijian AI public Agent Skills

Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow simulation and explicitly authorized broker execution.

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

An Innovative Agent Framework Driven by KG Engine

Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.

This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented Generation (RAG) pipeline.

Python SDK for transforming any AI agent into a production-ready application. Framework-agnostic primitives for runtime, memory, authentication, and tools with AWS-managed infrastructure.

Turn papers and research topics into source-linked commercialization assessment drafts. Python, FastAPI and CrewAI; auditable scoring, checkpoint recovery and durable request receipts.

A simple, yet powerful and extendable Slack bot

Framework for enhancing LLMs for RAG tasks using fine-tuning.

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

Conversational voice AI agents

[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

Your CrewAI Powered Video Editing Assistant

AI-based stock analysis and trading system

利用LLM构建应用实践笔记

AI Travel Agent

Practical LangChain patterns and implementations for real-world LLM applications. 极客时间：LangChain实战课 - 这是LangChain框架早期设计的一系列重点模块的直接而清晰的示例和讲解。随着LangChain的快速演进，有些代码需要安装新的版本进行迭代。希望大家在快速浏览课程概念（仍有价值）的同时，自行学习LangChain最新的代码和进展。

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

中文领域心理健康对话大模型SoulChat

一个优雅且完备的 Python QQ 自动化框架，基于 Mirai API HTTP v2。 Powered by Graia Project.

A cache for AI agents to learn and replay complex behaviors.

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.

Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.

SEO agent skill for OpenClaw,Claude Code, and AI agents. Generate beginner SEO audits and advanced technical SEO reports for any page.

Cognitive Architectures for Multi-Agent Teams

One API for all LLMs either Private or Public (Anthropic, Llama V2, GPT 3.5/4, Vertex, GPT4ALL, HuggingFace ...) 🌈🐂 Replace OpenAI GPT with any LLMs in your app with one line.

Bridge between LLM-Agent and Cadence Virtuoso. A new infrastructure for Agentic Analog and Mixed-Signal Design.

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时：快速开发、验证和恢复复杂 AI 工作流，并将其稳定交付为服务。

:newspaper: Let ChatGPT Summarize Hacker News for You

See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.

Repo containing code for multi-agent deep reinforcement learning (MADRL).

self-improving agent

Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

[CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction

Full Stack application for retrieving Stock Data and News using LLM, LangChain and LangGraph

Build autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.

Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.

ChatGPT Team(Business) 促销码自动扫描工具 — 批量发现/验证/价格收集，支持 17 国 34 个码，最高折扣 71% | ChatGPT Business promo code scanner — batch discovery, validation, price collection, 34 codes across 17 countries, up to 71% off

Wise and powerful personal assistant, available in your nearest terminal

If you can read ~100 lines of Python, you understand agents.

A research project for natural language generation, containing the official implementations by MSRA NLC team.

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seamless integration with existing OpenAI SDK clients while leveraging the power of local ML inference.

Run Hermes Agent and OpenClaw on the same WeChat account

transformers pytorch mpt text-generation code custom_code

Chat with your documents offline using AI.

Visualization and debugging tool for LangChain workflows

End-to-end Generative Optimization for AI Agents

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

An old coder's strategy for the agent era: don't read the code — make it run the gauntlet. Evidence-first development skill for coding agents, inspired by Uncle Bob.

TTSFM mirrors OpenAI's TTS service, providing a compatible interface for text-to-speech conversion with multiple voice options for free.

Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

AGI 社交网络 Bot. BiliBili | 直播聊天数字人 | 视频@自动回复 | 私信bot | 终端聊天 | 语音交互

Readymade evaluators for agent trajectories

开源、本地优先的 AI 求职与投递管理工具，支持简历管理、刷题练习、模拟面试、面试复盘、Offer 对比与谈薪指导。Open-source, local-first AI job-search workspace and application tracker with resume management, practice questions, mock interviews, interview reviews, offer comparison, and salary negotiation guidance.

JamTools是一个跨平台的小工具集类软件，支持Windows7/8/10/11、Macos、ubuntu系统(其他系统可以直接从源码编译打包)。包含了(滚动/区域)截屏、录屏、文字识别、多种语言互译、多媒体格式转换、鼠标键盘动作录制播放、局域网文件传输、聊天机器人等功能，完全开源!

browser controlling AI agent that applies to relavant jobs on internet autonomously. join chat @ https://discord.gg/umgnyQU2K8

一款证据驱动的 FOFA 资产测绘智能体：支持自然语言侦察、AI 反思、CLI / MCP / Skill / REST API，以及经人工审批的 Nuclei 扫描。

An open source implementation of code execution with MCP (Programatic Tool Calling)

Find zero-days while you sleep. DeepZero is an automated vulnerability research framework that parses, decompiles, and analyzes thousands of Windows kernel drivers for exploitable IOCTLs natively using AI agents.

Open Source Company Brain

freephdlabor: customizing personalized multiagent systems that researchs 24/7 on your own scientific problem

Battle-tested agent skills mapping the footguns of Kotlin, Compose Multiplatform and the desktop JVM — mined from a production music app, not from documentation.

Give your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.

transformers safetensors qwen3_5_moe image-text-to-text qwen world-model

Command-line interface for ChatGPT, Claude and Bard

13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents.

An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and other AI coding assistants that support the Skill protocol. Once installed, the AI assistant can directly operate compilers, debuggers, and communication buses, automating the full workflow from code generation to hardware verification.

An Educational Project (step by step) to teach how to build a production-ready app for RAG application.

Free AI agent skills for Amazon sellers— keyword research, competitor analysis, listing audit & more. Works with OpenClaw, Claude Code, Cursor, Windsurf, Codex and any agent that supports the Skills format.

Agent that empowers software testing with LLMs; industrial-first in China

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP tools.

Robin: A multi-agent system for automating scientific discovery

Autonomous Android and computer use using any LLM (local or remote)

AI video processing pipeline for generating vertical shorts using LLMs, Whisper transcription, highlight detection and automated editing

An LLM Based Diagnosis System (https://arxiv.org/pdf/2312.01454.pdf)

Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.