GitHub agents

A buddy check for your prompts — before they reach an LLM. On-device, reversible anonymization that catches the PII you didn't mean to send.

Scalable Agentic RAG system using Pydantic AI, FastAPI & pgvector. Modular, production-ready foundation for document-based AI apps

Refactored fork of the sourcemap-leaked Claude Code CLI

Self-evolving AI-Framework for Autonomous Scientific Research (ASR) that writes, runs, and improves its own multi-agent workflows. Powered by MCP tool discovery and Darwinian evolution.

AI-Suite - n8n, OpenClaw, Open WebUI, OpenCode, Llama.cpp/Ollama, Flowise, Langfuse, MCP Gateway and more!

An open-source, AI-driven Social Media Digital Twin powered by LLMs (Ollama, vLLM) for Computational Social Science simulations, network analysis, and human-agent interaction.

Multi-tenant AI sales agent for Telegram, Instagram, WhatsApp & Web. Drop a YAML, get a bot. Built on LangGraph.

Local-first beat library built for producers — catalog, BPM/key analysis, license tiers & PDFs, tagged-MP3 + loopkit export, and assisted multi-platform publishing. Chat with your catalog via a built-in AI Agent (Claude · ChatGPT · DeepSeek), or wire it to any MCP client. Desktop + web.

OpenStreetMap MCP server providing precision geospatial tools for LLMs via Model Context Protocol. Features geocoding, routing, nearby places, neighborhood analysis, EV charging stations, and more.

Open-Source Framework for AI-Driven Quality Assurance. No-Code AI Agents for QA Testers. Automate Web, API, Database, and Mobile testing with natural language.

Stock research skill for AI agents — A-share, HK, US. Plan → fetch → validate → report.

Context compiler for TypeScript/JavaScript AI agents. Automatically compiles agent state into optimized LLM payloads with history compression, tool pruning, multi-provider support, and more.

Production text-to-SQL agent for Databricks, Snowflake, and AWS — safety guardrails, schema-aware, deployable in one command

A declarative meta-language for orchestrating multi-agent workflows. Readable by humans. Executable by LLMs. Portable across models.

AI image inspiration atlas · 3,800+ GPT-Image-2 works across 445 themes with full copy-paste prompts · MIT + CC BY 4.0

[CVPR 2026 Highlight] ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

GeneXus 18 MCP server for Claude, Cursor, and AI agents — read, edit, analyze KB objects (transactions, web panels, procedures, SDTs) over the Model Context Protocol.

Super Publisher 是一个专为 Agent 设计的插件，旨在实现自动化的多平台内容发布。

🪞 Agentic AI chat client for macOS, iOS, and watchOS, built with SwiftUI

Currently undergoing a large scale refactor as of 7-18-26 Check docs --- GraphLink (formerly Graphite) is a local-first, graph-based AI workspace for building branching reasoning workflows, running agent plugins, and orchestrating multiple AI providers in a visual environment designed for complex problem solving.

AI-powered interactive RPG engine with persistent memory, independent NPC minds, creativity-based combat, and a reactive world. Build scenarios, live adventures — the AI narrates everything. Supports DeepSeek, Anthropic, and OpenAI.

An agnostic AI-driven exploratory test framework that intelligently explores, tests, and validates any application

DJ Claude — the only music MCP server with multi-agent collaboration

Loop-Driven Development with OpenCode

Math models that make AI engagement feel human

🏛️ Belief Archaeology - An AI Agent skill that excavates hidden worldviews from YouTube videos instead of summarizing them. For Antigravity / Gemini CLI.

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.

The open-source Claude Code GUI — parallel multi-project sessions, multi-engine BYOK (Codex / DeepSeek / Kimi / Ollama), terminal, browser & DB bubbles, code review. Built on the official Claude Agent SDK. Local-first, MIT.

Python Low-Code System Solutions

Multi-agent cryptocurrency intelligence system built with Claude Code. 6 AI agents, 66 MCP tools, Agent Teams, zero orchestration code.

🎮 34 production-grade Claude Code skills for indie game development — studio agents, workflow skills, engine specialists, genre packs, and CI validation. From concept to launch.

MCP server giving LLMs the ability to design, simulate, and analyze SPICE circuits via LTSpice and NGspice

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right where the code lives. It increases productivity, reduces implementation errors, and helps keep changes aligned with the project’s intended design.

Run Claude Code from your Even Realities G2 AR glasses. Voice-first, hands-free, billed against your Claude Max subscription.

CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a stable JSON envelope and MCP.

Open-source AI social-media workflow engine for planning, drafting, brand voice, image generation, and platform-aware content automation.

Personal AI butler powered by Claude — task management, Claude Code sessions, memory system, and web UI. Self-hosted, local-first, open source.

[Agentic AI-RPG] Agentic AI role-playing game framework — narration, NPCs, lore, and character creation are autonomous plugin agents. Build interactive fiction with DeepSeek / OpenAI / Anthropic / Qwen.

A coding agent CLI with the ability to autonomously create/evolve skills and manage the lifecycle of reusable skills.

Climb from LLM API to RL Agent with Klara

The AI agent memory layer you can audit — local-first memory governance for AI agents: citations, trust policies, trace receipts, rollback. SQLite, sidecar-first, OpenClaw plugin.

MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF, and HTML output. For authors and platform teams; CI-ready, no cloud API.

[Open Source] Novel Writing & AI Programming Assistant. 【公开源码】的小说写作与 AI 编程助手。Aggregates top large models from home and abroad聚合国内外顶尖大模型 (DeepSeek/Gemini/Claude/Kimi/ChatGPT, etc.)

Explores the implementation of a LangChain Agent using Azure Cosmos DB for MongoDB vCore to handle traveler inquiries and bookings. The project provides detailed instructions for setting up the environment and loading travel data, aiming to empower developers to integrate similar agents into their solutions.

[CVPR 2026 Highlight] Offical code for- NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code

A monorepo for creating, managing, and publishing reusable Agent skills (Claude Code skills).

Agentic Devops using Claude + Org Mode

Your full-service AI agency. 8 teams, 113+ agents, 9 workflows. Clone it, open in Claude Code, say "onboard" — zero setup, zero API keys, just results. v2: Research team, credit-saving guide.

A toolkit for systematically checking proofs in statistics and ML-theory paper appendices using coding agents. Includes severity framework, phased parallel execution, auto-planning prompt, and a complete worked tutorial.

Terminal UI toolkit for agentic and chat apps, built on rich + prompt_toolkit.

Run AI coding agents (Claude, Codex, Gemini …) unattended — auto-answer prompts, auto-retry on rate limits, and list/tail/steer every agent locally or from agent-yes.com

A browser extension that allows you to highlight, tag, annotate, and export the best parts of your favorite YouTube videos and summarize these snips with the power of AI. Winner of Boost Hacks

Magento 2 extension to generate product short/long descriptions and product images with OpenAI (ChatGPT), Anthropic (Claude) & Google Gemini. Customizable prompts, multiple models, and clean HTML output. Save time and enhance your catalog with AI.

IELTS listening, speaking, reading and writing modules practice and evaluation with IELTS band calculation based on speech and text analysis and evaluation.

A CLI based agentic skill that manages your wiki for you, works with LLMs of your choice

A powerful Retrieval Augmented Generation system that turns your Markdown documentation into an interactive knowledge base using vector search and LLMs.

MemSearcher is a search agent that keeps a compact, iteratively-updated memory instead of the full interaction history, trained end-to-end with multi-context GRPO.

TriLane: autonomous AI pentester and multi-agent security auditor for authorized gray-box testing of web apps and APIs. Built with Rust and Tauri.

AgentAPI is a lightweight Python framework for building agentic AI backends and chatbots with minimal configuration. It provides a plug‑and‑play developer experience for integrating multiple LLM providers, creating AI agents, streaming responses, managing tools, and handling conversation memory --- all on top of FastAPI.

Benchmark suite for evaluating agent and LLM memory systems

Single source of truth for GenAI and agentic AI security incidents, mapped to OWASP LLM Top 10, OWASP Agentic Top 10 (ASI), NIST AI RMF, and MITRE ATLAS.

[ICML 2026] E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent Memory

A Rust-based lightweight Agentic Development Environment (ADE) that boosts your productivity with a persistent multi-pane workspace, built-in tools, and one-click remote access so you can keep working from your phone, anywhere.

General-purpose agent superteam for Claude code - contract-gated verification loops with warm-start local wiki for self-evolving, and structural prevention of premature exits.

Awesome A2A Agents is a curated list of tools, frameworks, and projects built on the Agent-to-Agent (A2A) communication protocol. It aims to showcase interoperable agent systems, share best practices, and help developers explore the emerging A2A ecosystem.

Achieve infinite conversation turns in a single API request via turn-mcp. Self-hosted MCP server with browser console for human-in-the-loop AI agents.

The command center for n8n automation operators: multi-instance management, real-time error tracking, AI-assisted debugging, a Code Lab, and one-click container deployment. Self-hosted, source-available (MIT).

Save 87% token usage for Claude Code. Zero install. 8 rules covering input+output+context. 6 months verified.

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Auto-evolving LLM Agent Harness - Benchmark-driven evolution via Claude Code + self_evolution.md guide

Official implementation of LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Agentic Reinforcement Learning 101. A pragmatic course for AI/ML Engineers based on "The Landscape of Agentic Reinforcement Learning for LLMs: A Survey" https://arxiv.org/abs/2509.02547

🍌 Autonomous story agent creating illustrated storybooks with Claude Code SDK

Benchmark Everything Everywhere All at Once, a fully autonomous agentic system for benchmark construction and customization.

Multi-agent orchestration plugin for Factory AI Droid CLI. 32 droids, 35+ skills, autopilot & ultrawork modes. Based on oh-my-claudecode.

Learn Claude Code — 基于源码的完整技术分析文档集，15章深度解析 Agent Loop、工具系统、权限系统等核心机制

Claude Code Manager - sessions, MCP, skills, usage & accounts in your VS Code sidebar. 100% local.

A personal AI agent operating environment you self-host on Cloudflare.

AI-assisted XAUUSD daily research workflow with Research Skill, Agent Harness, LangGraph, Tool Calling, and free public data sources.

High-throughput, self-hostable LLM router in Go. BYO provider keys, k8s-native, key pooling + batch + usage observability.

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

让 AI 像真正的团队成员一样参与项目、执行任务、协作交付的 AI Native 工作平台。

Shorter replies with Claude Code. Save output token spend.

Open-source A-share AI research workstation — multi-agent analysis, simulated trading loop, personal knowledge base; runs fully on your machine.

🚀 精选 Claude Skills、Agent Skills、LLM Skills 及 AI 智能体开发资源列表（中文）。A curated list of awesome Claude / Agent / LLM Skills.

Lynn: open-source desktop/CLI AI Agent with GUI Session Map, headless workers, realtime voice, long-term memory, Brain V2 routing, local 27B/35B GGUF support, and contract-based Agent Regression Kit.

AI 网文长篇小说写作流水线，12 个 skill 包。配套站点 novelcatch.com：番茄每日扫榜 / 拆书 / 情报（免费）

Open-source AI front-office factory for agencies serving local businesses: website, booking, intake, CRM, and agents in one workspace. Self-hostable.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on collected agent rollout trajectories.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

Turn tab overload into a local-first workspace with intent-first AI organization and Agent collaboration through MCP.

SOTA communication-efficient, fast, and robust map merging using 3D point cloud (accepted in IJRR)

Mission control for every Claude Code session on your machine.

Observable diagnostics, failure attribution, metrics, and no-key replay for multi-agent runtimes.

Self-hosted multilingual (English + 5 Indic) phone voice agent template - LiveKit Agents + Sarvam STT/TTS + OpenAI + Vobiz SIP. ~700ms-1.2s latency, under Rs 5.5/min. Demo: a real-estate site-visit booking agent.

Claude Code skill that deploys 8 radically different visual direction demos in an existing Next.js + Tailwind project, from Swiss Minimal to Neo-Brutalist. Compare them side by side, pick one, and it extracts the Tailwind config, CSS variables and base components.

Real-time trustworthiness evaluation and safety interception for AI agents. Semantic analysis, safe alternative suggestions, multi-step attack chain detection, and LLM-as-Judge.

Autonomous red teaming and evidence-backed security evaluation for live AI agents.

Agentic Framework which automates Software Testing Processes