Python agents

The operating system that AI workflows trust. Structure messy inputs. Establish identity. Track provenance. Build the durable data layer your AI workflows need to be trusted, reusable, and auditable.

The minimal AI agent engine

Open-source serverless runtime for AI agents. Bring any framework, get a production HTTP server with SSE streaming, sessions, auth, and memory.

Tune your AI Agent to best meet its KPI with a cyclic process of analyze, improve and simulate

A plugin helps ChatGPT to interact with IoT devices.

🌟Official code of our AAAI26 paper 🔍WebFilter

This code is the result of the collaboration of RL Turkey team.

a boilerplate for developers who want to start building an AI agent cluster with A2A and MCP servers integration faster and more efficiently.

The code for paper "EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning"

A CrewAI script that uses 4 agents and 4 tools to research your next steps for your personal brand

[AAAI 2023 Oral] Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition

Rational OpenCog Controlled Agent (ROCCA). Use OpenCog to control a rational agent in OpenAI Gym and Malmo environments.

🐧Operator-Use: AI that can do stuffs on your computer

Automatic subtitles for DaVinci Resolve with OpenAI Whisper

Claudetools is a Python library that enables function calling with the Claude 3 family of language models from Anthropic.

Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.

A comprehensive collection of n8n automation templates featuring AI agents, RAG systems, and enterprise workflows. Includes integrations for Gmail, WhatsApp, Telegram, Slack, and more. Future-ready automation solutions for 2025.

This repository is an open-source showcase of A2A-based AI agents that implement HTTP Message Signatures for authenticating their requests

Multi AI agent system for financial analysis with CrewAI

[ICML 2025] "From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium"

OpenClaw 贾维斯看板是一个面向 OpenClaw 多 Agent 系统的实时作战指挥中心。 它提供系统健康、Agent 运行态、任务管理与多模型用量看板（MiniMax / OpenAI / Gemini / GLM）的统一视图，支持本地 API、实时刷新与可视化配置，帮助你在一页内快速完成监控、诊断和操作。

MASTERKEY is a framework designed to explore and exploit vulnerabilities in large language model chatbots by automating jailbreak attacks and evaluating their defenses.

Open source product copilot. Embed an AI chat widget that doesn't just answer questions—it executes client-side actions in the user's browser to get things done inside your app.

🚀 Lightweight Python library for building production LLM applications with smart context management and automatic token optimization. Save 10-20% on API costs while fitting RAG docs, chat history, and prompts into your token budget.

OpenClaw AI Trading Agent, based on EVPlus.AI data.

An AI-powered solution designed to enhance mobility for visually impaired individuals by combining real-time video analysis with voice-guided navigation. Also features a built-in Multi-Agent AI Assistant — users can speak naturally to complete map navigation, adjust system settings, send messages to family.

一个基于 **LangChain 1.0**、**阿里通义 Qwen** 和 **MCP(amap-maps)** 的旅游规划 Agent Demo，支持： - 并行调用高德地图相关工具（搜索 POI、路线规划、天气查询） - 中间件级别的城市约束、工具预算控制、输出城市安全检查 - Gradio 前端，支持流式对话与调试日志查看（开发者模式）

Let codex (main agent) collaborate with claude code Through codex skills

A terminal AI that doesn't babysit you. sot-cli gives LLMs full power, a novel memory architecture that slashes token costs, and agent orchestration, all from a single Python CLI. No guardrails, no bloat, no frameworks. Just raw AI power at your fingertips.

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

Model Context Protocol (MCP) server for mapping clinical terminology to Observational Medical Outcomes Partnership (OMOP) concepts using Large Language Models

Open-source, self-hosted AI agent that evolves its own code to perform better in your specific use-cases.

A Claude Code Marketplace

AI-powered chatbot designed specifically for legal professionals. It aims to streamline client interactions, provide preliminary legal guidance, and enhance law firm efficiency. The chatbot offers features such as legal document analysis, client intake automation, legal research assistance, appointment scheduling, multi-language support,.

CLI-based multi-agents for Auto-Tuning (e.g. HPC code optimazation loops) supporting Local LLMs

CLI for agent builders to benchmark & chaos test your AI Agents. Text, Voice, Code supported.

Atlan AI Agent Toolkit

Agent skill for fast, cheap market research using LLM synthetic surveys + Semantic Similarity Rating (SSR). No API keys needed.

该企业智能办公智能体项目深度融合了LLM、向量数据库与语音识别技术，为企业提供了统一、智能的信息处理与决策支持中心。该系统核心具备三大能力：1. 它能构建企业专属知识库，通过对PDF、Word等文档的智能解析与检索，让员工能通过自然语言快速获取精准的政策、流程信息。2. 它打通了企业数据孤岛，用户可以用日常语言直接查询多个业务数据库，极大降低了数据获取与分析的门槛。3. 它提供了高效的会议管理功能，能将音频内容自动转写并提炼成结构化纪要，确保会议要点一目了然。项目采用Streamlit构建直观易用的Web界面，以LangChain为应用框架，后端集成DeepSeek大模型、BGE嵌入模型与百度语音识别服务，实现从文档、数据到语音的多模态信息交互，旨在成为企业数字化转型的强大AI助手。

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

[CVPR 2026] Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation

A research framework for evaluating proactive AI assistants through active user simulation

Agentes legales de IA para derecho español — Adaptación de claude-for-legal de Anthropic al ordenamiento jurídico español. 20 módulos, 100 skills, 17 agentes programados.

Real-time system audio translation for macOS — translate any audio (YouTube, podcasts, meetings) live on screen with OpenAI or Google Gemini. On-device speech recognition; optional low-latency realtime mode.

Framework for building continuous-loop autonomous AI agents.

Claude Code skills for founders building B2B SaaS — covering GTM, product, engineering, design, and content.

Model Context Protocol (MCP) server that gives LLM agents and chatbots direct access to the World Bank's Data360 Platform. Search, validate, and retrieve development indicators—from GDP and poverty to gender equality and climate—with structured metadata and time-series data, without hallucinating values.

An AI-powered DJ mixing system that crafts custom mixes from your local MP3s using natural language prompts, analyzing BPM, key, and energy for seamless transitions like crossfade and EQ sweep. Ideal for personal use, it generates a mixed MP3 and detailed JSON setlist/planning files.

🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order through machine approval, the LLM never on the order path. Multi-market, audit-grade.

全球酒店实时推荐及闭环预订Skill，200 万+酒店，全球第三大酒旅B2B公司数据源，免费无调用上限。可按地点、日期、星级、人数、标签等条件搜索酒店列表，返回候选酒店及展示价。可查询指定酒店的实时房型列表、价格计划和取消政策。可锁定价格，创建订单+支付宝二维码，并查询历史订单。

Local-first AI contract review agent that turns legal templates and counterparty drafts into clause-level analysis and tracked-change DOCX redlines.

Provide different cloud products MCP Server tools to help developers manage cloud resources with AI-agent

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Stop trusting single AI outputs. An anti-hallucination framework with dual-brain arbitration, multi-model audit, and evidence chains for LLM quality control.

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

AgentMill - Enterprise-Grade AI Agent Platform & Agent Factory for Building Custom Digital Employees

A self-evolving knowledge accumulation & hybrid retrieval system for AI coding agents (Claude Code / Codex / etc.)

OneCode 是一个参考Claude Code实现的Code Agent。它用可控的工程框架约束大模型完成编码任务。它的主循环采用 Hooks 机制实现扩展，通过上下文工程与工具调用支撑任务；运行状态可中断、可恢复，并提供结构化的 trace 与 error log 用于观测与回放。可用于学习与二次开发。

An asynchronous file-based handoff protocol for Claude Code and Codex agents sharing one project workspace

The AI-native technical SEO crawler. Open-source MCP server for Claude / Cursor / Codex — 37 tools, 50+ checks, unlimited pages, WAF detection, ephemeral by design. Built on LibreCrawl. MIT.

The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"

AI Infrastructure & DevOps Roadmap covering Linux, Kubernetes, Local LLMs, AI Agents, RAG, AI Observability, Security, and production-grade AI platform engineering projects.

Windows Computer Use for AI Agents. Both a tool (22 MCP tools for click, type, screenshot, OCR, UI inspection) and an agent (autonomous mission engine, macro recorder, intent-based discovery, event watchers). Built with opencode (DeepSeek V4). Ships as MCP server, web UI, and Tauri desktop app.

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

🦅 5-Layer Intelligent Skill Retrieval for Hermes Agent — hard triggers, FTS5, synonym dictionary, dense embedding, RRF fusion. Zero core modification.

gradio region:us

gradio region:us

static region:us

safetensors qwen3_next text-generation conversational arxiv:2309.05516 base_model:Qwen/Qwen3-Coder-Next

transformers safetensors llama text-generation code granite

gguf merge programming code generation code codeqwen

Django manage.py context for coding agents — and tab completion for you

🐧Operator-Use: AI that can do stuffs on your computer

Hermes-first operational AI substrate with filesystem-grounded memory, governance, persistent routes, and recoverable agent continuity.

Give Claude Code a persistent memory — it remembers you, your projects, and your decisions as plain Markdown files you own. Fully local. Just say `start`.

A disciplined, delegation-driven operating system for AI coding agents. npx contractor-kit.

Reflective memory for agents

GEZHI (格致): a scholar-centered agent architecture for traceable, reviewable, and verifiable empirical social-science research.

Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.

Claude Code skill for interactive learning with FSRS-6 spaced repetition, research agents, book catalog, ADHD-aware sessions, and domain-specific visualization

AI agent skills for claude code that generates comprehensive wiki-style markdown document for codebase, with CI/CD-ready incremental updates

OpenTelemetry integration for AI Agents Cursor / Copilot / Gemini / Claude / Codex that records agent activity and exports detailed telemetry with OTLP protocol

🕸️ Engineer the organization, not just the agent. 591 curated resources · 9 design layers · 11 sections · 273 papers & preprints — a field guide, CC0 open dataset, and interactive atlas for graph-structured multi-agent systems: roles, topologies, handoffs, work graphs, state, gates, reliability, observability.

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data

Compact AI agent runtime control plane with governed tools, HITL approval, resumable execution, trace-driven evaluation, and SWE-bench-shaped evidence.

通用视觉识别 Skill 模板：为无多模态能力的 AI agent（如 DeepSeek）补上图片识别能力，支持本地图片与 URL。纯净模板 + scripts/setup.py 一键配置 Key/端点/模型，遵循开放 Agent Skills 标准，兼容 Claude Code / Codex / OpenClaw / Reasonix。

An agentic mobile security research system built as a Claude Code project. An orchestrator spawns focused sub-agents, each with one narrow objective.

MedMCP: An Open Agentic Ecosystem for Medical Imaging Workflows

Agent skill for AI trip planning (Claude Code · Codex · Gemini CLI · Cursor · Copilot · any SKILL.md agent) — verified, bookable itineraries: hour-by-hour days, real flight prices, offline KML maps, eight themed page designs · 旅行规划 / 行程 / 机票比价

🎮 Production-ready AI rules for Unity 6.2+. Single Source of Truth for Cursor (.cursor) and Google Antigravity (.agent) with auto-sync workflow.

Tutorials, example projects, and reference code for practitioners building and operating agents with Rasa. Companion to rasa.community. Maintained by Rod Rivera.

The open-source agentic framework to build, orchestrate, and operate production AI agents.

Reference architecture, contracts, skills, and fixtures for safe evaluator-driven self-improving ecosystems.

墨枢是一个面向中文长篇网文作者的 AI 小说写作工作台，支持作品大纲、章纲、人物与世界观设定库、时间线、RAG 检索、一致性守卫、自然化审查、AI 辅助续写、团队协作、用量计费，以及面向漫剧改编的静态分镜管理。前端采用 Vue 3，后端采用 FastAPI，支持 PostgreSQL/pgvector、Redis、Docker 自部署和 Cloudflare Workers 预览。

Beyond RAG: An open-source agentic healthcare search framework using Gemini and Google ADK for query fan-out, evidence retrieval, grounding, citation evaluation, and trustworthy healthcare information discovery.