GitHub agents

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

AI-powered assistant that turns your project context into end-to-end test strategies, detailed scenarios, and ready-to-run boilerplate across popular frameworks.

Implementing Skills functionality for your agents

Harnessing the Memory Power of the Camelids

Resumable, traceable AI coding — decisions and history stay with the project

Evoplex is a fast, robust and extensible platform for developing agent-based models and multi-agent systems on networks. It's available for Windows, Linux and macOS.

Machine Learning and having it Deep and Structured (MLDS) in 2018 spring

基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs

CLI to convert natural language to terminal commands

🤖💡📱 ChatGPT mobile app built using Expo/React Native

SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. SmartPlay is designed to be easy to use, and to support future development of LLMs.

This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix some of the annoying things you get from only using Claude code out of the box

Chat Relay is a system that allows Cline/RooCode to communicate with web-based AI chat interfaces (like Gemini, AI Studio, ChatGPT, and Claude) through an OpenAI-compatible API. This enables using models that may not have public APIs through their web interfaces.

tensorflow reinforcement learning agents for OpenAI gym environments

Prompt Line is a macOS app developed to improve the prompt input experience in the terminal for CLI-based AI coding agents such as Claude Code, Codex CLI, and Gemini CLI.

A set of prompts and agents that process daily journal entries

Universal LLM Interface

Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Code can spawn subagents via Task(). These are the prompts those agents receive.

基于 UI Automation（UIA）的 QQ 聊天机器人完整实现，支持 AI 自动回复与表情包发送。 只需配置 API Key 并绑定 QQ 输入框、聊天列表和发送按钮即可使用。 本项目对 QQ 实现零注入、零内存读写，是目前最安全的 QQ 聊天机器人实现之一。

Turns AI agents from chaotic code generators into disciplined engineers. 12-stage workflow from research to production.

Unified AI SDK for Swift, bringing the power of Vercel AI SDK to Apple platforms

An MCP server for public & prediction markets research. Ask natural-language questions and get structured, source-backed answers across SEC filings, earnings transcripts, company financials, stock & crypto market data, and prediction markets news & research. Built for investors, analysts, and researchers who need fast, cited intelligence.

Fenix Ai Trading Bot with LangGraph and ollama and multipe providers

From Java Dev to AI Engineer: Spring AI Fast Track

🐮 Build distributed, event-driven agents

Git primitives for autonomous coding agents

A private, modular node based AI workspace for thinking and creation. Seamlessly connect to Ollama, OpenAI, Gemini, Anthropic, and Groq models in one unified, node-based interface for reasoning, visualization, and exploration — all running locally or via API.

Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more.

Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.

One Page Agent.The browser-native workbench that lives in One Page.

Git-native context control plane for AI coding agents

Awesome QA Skills — a bilingual (zh/en) AI testing Agent Skills library for Codex, Cursor, Claude Code, Kiro, OpenCode, and Trae. Ships 4 testing workflows and 25 testing-type skills (58 skill folders with language parity): independently installable, composable, and eval-ready with skill-up. Covers requirements, strategy, cases, API/performance/sec

Curated collection of modular agent skills for LLM-based agents

Open-source implementation of SeaSeed.ai v1.0 (codename: Clawerse). AI ocean world platform for multi-agent social, tasks and compute collaboration.

On-board AI agents autonomously saving satellites from orbital debris @ treehacks 2026

Browser extension and framework to use and build AI assistants for any web application

Implementation of Toolformer: Language Models Can Teach Themselves to Use Tools

A Chatbot for ordering a pizza that demonstrates how using the IBM Watson Assistant Slots feature, one can fill out an order, form, or profile.

CrawlAI RAG is an AI-powered website intelligence platform that allows users to crawl entire websites, index their content, and ask natural-language questions using Retrieval-Augmented Generation (RAG). It transforms static websites into queryable knowledge bases.

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

Chat with GPT LLMs over voice, UI & terminal, all with access to the internet. Powered by OpenAI.

PHP SDK for Claude - Provides complete 1-for-1 functionality of the Official Python SDK

multi agent RL for traffic light control in Sumo using distributed PPO

bumpgen is an AI agent that upgrades npm packages

Curious about Generative & Agentic AI? In this beginner-friendly series, we'll break down the basics with fun doodles and simple explanations. First, you'll get the core ideas, then we'll explore how they connect to real-life examples you can actually relate to.

The LLMs' framework optimized for ultra-fast response times.

🧾✨ AI-Powered Receipt and Invoice Scanner for Laravel, with support for images, documents and text

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

Openai-style, fast & lightweight local language model inference w/ documents

The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.

Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs" by Boris Ivanovic and Marco Pavone.

From isolated agents to shared work

Autonomous orchestration framework for Claude Code with MemPalace-inspired memory (4-layer stack, 818-token wake-up), parallel-first Agent Teams (6 teammates), Aristotle First Principles methodology, and 4-stage quality gates. 925+ tests, 22 active hooks, automatic learning pipeline.

An open standard for capturing the WHY in git history

MCP server for token-efficient large document analysis via the use of REPL state

A CLI/TUI app that orchestrates multi-agent conversations by enabling different AI CLI tools (Claude Code, Gemini, Qwen, etc.) to communicate in shared rooms.

Claude Multi-Agent Project Manager — multi-channel orchestration, GitHub-first SDK mode, and plugin system for Claude

DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. Analyze, summarize, and extract insights from a wide array of file formats, securely and privately, all offline.

MCP server for free Google AI Mode search with citations. Query optimization, CAPTCHA handling, multi-agent support. Works with Claude Code, Cursor, Cline, Windsurf.

172 expert marketing skills for AI agents — ClawFu MCP Server

The local-first intelligence layer that gives AI agents durable continuity, explainable retrieval, portable context, and verified learning across harnesses.

MCP server for controlling a real iPhone via macOS iPhone Mirroring...and any MacOs app. Screenshot, tap, swipe, type — from any MCP client.

Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker command.

Fast, privacy-first desktop & web UI for self-hosted Honcho — browse memories, peers, sessions, conclusions, and chat with memory context.

🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applications

MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run numerical simulations through natural conversation

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.

Pre-install security scanner and guarded installer for Agent Skills. Quarantine, scan, enforce policy, and verify skills before they reach Codex, Claude Code, Cursor, Gemini CLI, or OpenClaw.

This project enhances the construction of RAG applications by addressing challenges, improving accessibility, scalability, and managing data and user access. It uses Django, Llamaindex, and Google Drive for effective database management.

Dynamic decentralized task allocation algorithms for multi-agent systems using auctions

Generate knowledge graphs. Inspired by @yoheinakajima instagraph.ai

An example of making a Figma plugin that talks to OpenAI GPT models.

Tool that just makes your open source project better using LLM agents

Bridgic is the next-generation agent development framework for building intelligent systems.

🥥 Coco AI Server - Search, Connect, Collaborate, AI-powered Enterprise Search, all in one space.

"Generative AI in Action" book's code repository

CRM Data Q&A Agent - Advanced RAG with NL2SQL over Salesforce Data

A lightweight annotation standard that helps AI agents navigate codebases faster, with fewer file reads and tool calls

Adversarial bug hunting skill for Claude Code. 3 isolated agents (Hunter, Skeptic, Referee) find and verify real bugs.

An agentic framework that helps developers build resilient agentic systems

AI VTuber Waifu and voice assistant

Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, and extend with modular features.

Framework and toolkits for building and evaluating collaborative agents that can work together with humans.

LLM-powered assistant for creating, editing, and interpreting business process diagrams

Orchestrate fleets of Claude Code & Claude Computer Use agents across containers, VMs, and physical devices. Live desktop streaming, intelligent task delegation, and multi-channel human-in-the-loop gateway. Schedule tasks with self-healing and self-learning.

Open-source AI-augmented Security Operations Center using LLMs + Multi-Agent Orchestration | Foundation-Sec-8B | Wazuh | TheHive | RAG

Global instructions for coding agents: evidence, parallelization, validation, all in one AGENTS.md / CLAUDE.md

Open-source AI canvas design agent — alternative to Lovart / CapCut Video Studio / Canva AI. Chat-driven image & video generation on an infinite canvas.

AI website cloner for rebuilding live websites with AI coding agents

基于原生 Spring AI 的智能体（Agent）开发框架，提供 ReAct 执行引擎、分层记忆、工具调度、Human-in-the-Loop 等核心能力，形成完整的 Harness Engineering 方案，帮助开发者快速构建 AI Agent，可以快速搭建 Java 版的 Claude Code。

Open-source AI browser for macOS. Agentic, local-first, native Swift.

OpenTelemetry-native LLM observability CLI. Point any OTEL exporter at it and watch your LLM/agent traces in real time.

Let AI write the code — you own the view. Termdock: the AI-native terminal for macOS & Windows. Claude Code / Codex / Gemini / GitLab Duo agent sessions, diff impact analysis, visual Git review, and a fully customizable backdrop (your images, themes, fonts). GPU-fast, battery-kind.

Proximal Policy Optimization (PPO) algorithm for Contra

A companion guide for the blog post series, LangChain Decoded.

CrewAI agents that can plan your vacation.

The security layer for AI coding agents : Skill governance, safe package recommendations, MCP/tools guardrails, secret protection, runtime policy enforcement and full audit visibility with a self-serve dashboard.

Natural Language Processing Chatbot for RocketChat

An easy way to build Whatsapp Chatbots on top of the new Whatsapp Cloud API