Custom agents

Open-source CMA-compatible agent runtime. Run multi-agent systems locally with any model (Ollama/vLLM/Claude/GPT), MCP tools, scenario templates, and a beautiful dashboard. One command start. Built for enterprise teams.

An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.

omg.dev — Remote control for claude, codex, cursor, opencode, pi, grok, jcode with mobile client

The Digital Being Framework for Autonomous Agents

A structural code search engine for Al agents.

SDK monorepo for the Ethora chat / messaging platform. (1) Pick an SDK for your frontend stack. (2) Integrate manually or with ethora-setup. (3) Optionally configure app settings, deploy AI agents etc. Server: ethora.com cloud (free), self-hosted (AWS, Docker, Helm, Cloudron) or a managed dedicated server with SLA. All options: ethora.com/get

PyTorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

ai agent that could talk to my gf thru my mac. went viral got like 20m views

AI assistant integration for n8n workflow automation through Model Context Protocol (MCP). Connect Claude Desktop, ChatGPT, and other AI assistants to n8n for natural language workflow management.

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

🤖基于.NET搭建的企业级中台AI知识库智能体开源架构：Skill、MCP、Qdrant、知识库、Agent、多智能体协同、聊天记录压缩策略、AI联网搜索、智能体权限管控、AgentFramework、RAG检索增强、知识库重排模型、本地Ollama AI模型（不联网）、智能体技能可控加载、智能体记忆、一库多租户、SignalR、AI语音电话模式、Hangfire、RabbitMQ、前端（Vue）

Chat snowflake - Text to SQL

一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !

AI agent for autonomous cyber operations

Scripts and Tweaks for running agents like OpenClaw, Claude Code, Codex, Hermes Agent, and more on an Android smartphone

AI 编程工具实战指南 — 66 个 Claude Code 技巧 + 10 款工具最佳实践 + 可复制配置模板 | AI Coding Tools Guide with 66 Claude Code tips

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Turn any website into a compact CLI tailored for AI agents. Browse the web in hundreds of tokens, not tens of thousands.

Open-source WYSIWYG .docx editor library for React and Vue with canonical OOXML, tracked changes, and real-time collaboration. Agent-ready.

面向基本面因子研究的智能体-A hypothesis-driven AI agent for fundamental factor research, with evidence-gated validation and research memory.

让 Codex、Claude Code 等 AI Agent 成为你的跨平台电脑维修助手：64 个按需加载的 Playbook，覆盖诊断、清理、性能、网络与安全维护——C 盘爆满、电脑卡顿、流氓软件、应用迁移、数据恢复都能直接问；先取证、再计划，确认后修改。

Terminal pixel-art office for AI coding agents

给你的 AI 一副身体，和一点人味 —— 会记事、会看场合的 QQ 陪聊 + 能控制安卓手机的 MCP

Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai

Richkware is a modern C++20 framework for building educational malware agents. It provides a comprehensive, secure, and modular architecture for understanding malware mechanics and cybersecurity defense strategies.

Framework for Multi-Agent Deep Reinforcement Learning in Poker

A project implementing various agentic RL based on the Slime post-training framework

BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications.

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.

The open-source operating system for physical AI.

"Aurogen🍊: The Multi-Agent Evolution of OpenClaw."

macOS 上的 Codex、Claude Code CLI 与 Claude Desktop 多实例管理器，统一管理账号、供应商密钥、独立配置、会话与代理。 / A macOS manager for Codex, Claude Code CLI and Claude Desktop instances, accounts, provider keys, isolated configs, sessions and proxies.

Powershell-based bot framework

One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体，一个对话框提供所有主流格式数据的见解，包括文档、数据库、业务系统和图像。

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.

One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体，一个对话框提供所有主流格式数据的见解，包括文档、数据库、业务系统和图像。

Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating them.

A Survey on Multimodal Retrieval-Augmented Generation

Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

Boss Skill - BMAD 全自动研发流水线（多 Agent 编排）

MiniMax M2.1, a SOTA model for real-world dev & agents.

200+ production open source Rails apps & engines in one repo. Search across real codebases with AI agents to research architectural patterns.

Custom plugins for hermes-agent — goal management, inter-agent bridge, model selection, cost control

Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC

Save tokens. Maximize context, Safely

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

KohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.

A chatbot implemented in TensorFlow based on the seq2seq model, with certain rules integrated.

An MCP server to query any Postgres database in natural language.

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

The AI automation platform, self-hosted. Describe the job in chat and LiveContext builds it: readable workflows, scoped AI agents, and small apps your team uses. Chat, Workflow, Agent and App on one canvas.

Building Open LLM Web Agents with Self-Evolving Online Curriculum RL

Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSeek 等国产大模型。技能/插件/跨会话记忆，8 层安全沙箱，数据不离开你的机器。Docker 一键部署，MIT 开源，零锁定。

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph.

Drop-in AGENTS.md that makes every coding agent behave like a senior engineer instead of an eager intern. Kills sycophancy, stops drive-by refactors, forces verification loops. Synthesizes Karpathy's four principles and Boris Cherny's Claude Code workflow. Works with Claude Code, Codex, Gemini CLI, Cursor, and the open standard.

103 paste-ready declarative agents for Microsoft 365 Copilot. No coding. No Azure. Deploy in minutes.

Mega is an open-source implementation of Google Piper — a Git-compatible monorepo engine built for the AI Agent era.

DDC Converters 2.0: RVT/RFA to GLB, IFC4 and JSONL; IFC to Excel; DWG to Excel, DXF and SVG. Offline CLI and desktop apps, n8n workflows and AI-agent instructions.

MCP (Model Context Protocol) server for game hacking & reverse engineering. A structured knowledge base of 4,100+ skills with full source code archives, specialized agents, and workflow tools -- designed to be plugged into Claude, Cursor, or any MCP-compatible client.

Comprehensive ML/AI interview codex with iterative system design, production-ready code, and 2026 standards. Includes LLM/GenAI, RAG systems, agentic AI, and algorithms from scratch.

Self-hosted web search skill for AI agents (OpenClaw/Claude Code/Antigravity) via SearxNG

An AI coding agent by JetBrains that ships code from your terminal, IDE, or CI/CD pipeline - powered by any LLM you choose

HeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline

🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node.js installer, MCP server, one-line install

小红书 CLI — 搜索、分析、自动化 Xiaohongshu content. Built for AI agents.

FPF (First Principles Framework) Library: methods and pattern languages for open-ended development and a shared culture of thinking and acting among people and AI agents. Use individual methods or combine them to solve difficult problems and expand capabilities.

Full agentic runs for Slay the Spire 2. A mod that exposes in-game state, and the MCP server for the mod.

首个中医大语言模型——“仲景”。受古代中医学巨匠张仲景深邃智慧启迪，专为传统中医领域打造的预训练大语言模型。 The first-ever Traditional Chinese Medicine large language model - "CMLM-ZhongJing". Inspired by the profound wisdom of the ancient Chinese medical master Zhang Zhongjing, it is a pre-trained large language model designed specifically for the field of Traditional Chinese Medicine.

🤖 A simple bot to translate JSON HTTP requests into Telegram push messages

An in-the-wild benchmark for AI agents in the production harness.

HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents

Plugin for Butterbase.ai

A multi-agent AUTO Research loop for idea discovery, experiment execution, evidence-grounded paper writing, quality audit, and live Web observation from AI group, CNIC, CAS.

Use Claude Code / CodeX CLI to perform multiple tasks in parallel with a Codex-style UI. Your personal codex/cursor-background agent. Claude Code UI.

[ICME 2026] Official implementation of Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

Agent Engineer - a practical course for software engineers

A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Stop hook for Claude Code that keeps the agent working until all plans and user requests are 100% complete

Collections of skills for building with ElevenLabs

Pocket-sized AI chatbot built using a RPI Zero 2w / 5

MCP server for AI agents that need a phone number: order a private number in 200+ countries, read the SMS verification code, hand it back. The widest country coverage in the category, and you can check it with one API call.

A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.

It's a go variant of Hells gate! (directly calling windows kernel functions, but from Go!)

Client for OpenClaw — Connect ClawWork to your own OpenClaw and unlock 10x multi-session productivity.