GitHub agents

A list of AI memory projects

A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

Empower agents with professional capabilities in specific fields (such as full-stack development, complex logic planning, multimedia processing, etc.) through modular Skills definitions, allowing agents to solve complex problems systematically like human experts.

AI coding agent that edits symbols, not strings. AST surgery, full LSP, and a live code graph wired to memory that resurfaces by file, co-change, and semantics.

ChattyUI - your private AI chat for running LLMs in the browser

The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.

An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

A minimalistic MCP client with a good feature set.

Life Agent RU YEE — An AI-powered life management agent that autonomously handles daily routines including meal planning, grocery shopping, schedule coordination, and household task automation via cloud-based mobile agents.

The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Agents Capable of Self-Editing Their Prompts / Python Code

Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.

High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 98+ document formats using streaming parsers and built-in OCR.

An End-to-End Infrastructure for Training and Evaluating Various LLM Agents

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

Agent samples built using the Strands Agents SDK.

AgnosticUI Local (v2) is a CLI-based UI component library that copies components directly into your project. Works with AI tools, agent-driven UIs, and prompt-ready workflows.

山音超级编剧大师——由 @山音 设计的全格式影视编剧技能。 覆盖从1-3分钟概念超短片到90分钟电影长片、多集剧集的全格式剧本创作。 支持四种格式：概念超短片（how-to-tell/what-if）、5-10分钟叙事短片、90分钟长片（商业/文艺）、多集剧集。 覆盖从人物设计、结构大纲、场景拆解、到完整剧本写作的全流程。

Make Discord your LLM frontend - Supports any OpenAI compatible API (OpenRouter, Ollama and more)

Free AI Agents Resources – Your All-in-One 2026 Learning Hub

OpenCode quota & tokens usage with zero context window pollution. Supports OpenCode Go, Cursor, GitHub Copilot, OpenAl, Kimi Code, Alibaba Coding Plan, Chutes Al, Google Antigravity, Z.ai Coding Plan and more.

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.

Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes (Dense + Sparse + RRF + Reranker) across 7 languages. Ships as native MCP tools for Claude Code and Codex CLI.

Atom Agent, Open-Source AI Agent Platform for Self-Hosted Automation

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

An LLM-first SEO analysis skill for Antigravity, Codex, Claude with 16 specialized sub-skills, 10 specialist agents, and 88 optional utility scripts used as evidence collectors.

MCP Server for SearXNG

[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!

Use Claude Code for free in the terminal, VSCode extension, or via Discord

Sample Amazon Lex chat bot web interface

Angular 20 Starter with Node.js, Spring Boot, and AI (LLM, Voice, Podcast).

Llama 3+ inference in pure Java

🤖 功能丰富的微信机器人框架 | AI对话、对接Dify、积分系统、游戏互动、每日新闻、天气查询 | 非Hook非Web实现 | 支持 Windows✅ Linux✅ MacOS✅ | 全新架构解决XYBot第一代痛点！

☁️A native Android app for ChatGPT, Gemini, Claude, and DeepSeek ☁️ChatGPT、Gemini、Claude 和 DeepSeek 的原生安卓应用程序

知识图谱问答机器人，聊天机器人，基于知识图谱、语义理解等的对话机器人。

AI chatbot 🤖 for chat with CSV, PDF, TXT files 📄 and YTB videos 🎥 | using Langchain🦜 | OpenAI | Streamlit ⚡

日本語UIをAIエージェントに正しくつくらせるためのDESIGN.md集。Japanese DESIGN.md collection for AI agents — extending Google Stitch format with CJK typography.

Flexpilot - Open-Source, Native and a True GitHub Copilot Alternative for VS Code

A curated collection of awesome AI Agents and LLM Apps built with multiple tech stacks, showcasing real-world implementations using OpenAI, Gemini, local models, and various AI frameworks.

A self-hosted web dashboard for the Hermes AI agent stack. Provides a browser-based terminal, file explorer, session overview, cron management, system metrics, and an agent status panel — all behind a single password gate.

PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.

A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.

Convert any git repository into an engaging podcast

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

Command Your World with Voice

Debug your AI agents

High-fidelity HTML design and prototype guidance skill for AI agents

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

Payments are broken for AI agents. Snaplii unlocks real-world commerce with a safe, tokenized payment layer — powered by 500+ merchant gift cards — and is the only one that actually saves you money (up to 10% per transaction), on top of any existing deals or promotions.

Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.

ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offline-first RAG knowledge bases, ARGO becomes a DeepResearch powerhouse for autonomous thinking, task planning, and 100% of your data stays locally. Support Win/Mac/Docker.

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

AI handles execution, humans own the direction, and every run becomes an inspectable research artifact on disk.

Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019

Lightweight orchestration harness built for your AI agents. The unfiltered truth about where your project stands.

A hand-picked collection of tools and resources for Vibe Coding

pi coding agent in a technicolor web trenchcoat

🚀 告别多个App！本项目主要基于Python+React+TypeScript+Hono+SQLite3+Redis，打造“All in One”智能工具集。免会员破解爱奇艺、腾讯视频、优酷、抖音、B站、小红书等20+平台视频，支持4K在线解析与无水印高速下载。集成Cloudflare Turnstile防机器人和爬虫、Google、GitHub授权登录及OpenAI SDK、埋点SDK、MCP服务和Agent等，支持ChatGPT对话、AI绘画、论文降重、Hugging Face论文爬取、在线Latex编写；更有实时黄金K线、AI思维导图、闲鱼助手等效率黑科技。内置海量动漫漫画资源，畅享阅读！轻量高效，配置即用，完美适配PC与移动端，快来ChattyPlay开启奇妙之旅吧～

LangGraph template for a simple ReAct agent

End-to-end RAG system design, evaluation, and optimization. 极客时间RAG训练营，RAG 10大组件全面拆解，4个实操项目吃透 RAG 全流程。RAG的落地，往往是面向业务做RAG，而不是反过来面向RAG做业务。这就是为什么我们需要针对不同场景、不同问题做针对性的调整、优化和定制化。魔鬼全在细节中，我们深入进去探究。

Autonomous AI pentesting engine, continuous offensive security across web, cloud, identity, CI/CD, IaC, databases, Active Directory, Kubernetes and IoT firmware. Agentic reasoning plus real exploit execution deliver proof-based vulnerabilities. Privacy gateway: the LLM never sees your real IPs, host

BabyAGI: an Autonomous and Self-Improving agent, or BASI

SuperMew — Agentic RAG with LangChain & LangGraph

Claude Code like Sub-agents for Pi — parallel execution, live widget, custom agent types, mid-run steering and more ...

Blades is a Go-based multimodal AI Agent framework.

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security assessments, penetration testing, and bug bounty reconnaissance — without any API keys or cloud dependency.

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Bench 2 (GPT-5.5). Lifts GPT-5.4 69.7→77.0% over 10 iters, beats Codex/ACE/Training-Free GRPO; frozen harness transfers to SWE-bench-Verified.

Slack Bot Framework

structured extraction for llms

A comprehensive collection of Model Context Protocol (MCP) servers

MyAgents - 优雅、易用的 Agent 桌面端 ，一站式 Agent 工作台与任务中心

Connect and chat with your multiple documents (pdf and txt) through GPT 3.5, GPT-4 Turbo, Claude and Local Open-Source LLMs

Train Models Contrastively in Pytorch

Folder structure as agent architecture. ICM replaces framework-level orchestration with filesystem structure.

React Native binding of whisper.cpp.

🔥 This repository contains complete application examples, including websites and other projects, developed using Firecrawl.

Supercharge Claude Code with 11 AI agents, 36 commands & 15 skills — the claude-code plugin framework inspired by oh-my-zsh. 6-layer security hooks included. 5-min install.

Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

🤖 Beautifully designed chatbot components based on shadcn/ui

Bridge WeChat chat messages to any ACP-compatible AI agent (Claude, Codex, Copilot, Qwen, Gemini, OpenCode, OpenClaw, Hermes, Kiro, Kimi, Pi and more)

PlayGround: AI Research into Multi-Agent Learning.

AI-First Album: Chat with your gallery using plain language! LLM Vision + RAG + Album/Gallery.

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

Hypernetworks that update LLMs to remember factual information

Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero sharing. Your notes stay yours.

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.

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

Run MATLAB® using AI applications with the official MATLAB MCP Server from MathWorks®. This MCP server for MATLAB supports a wide range of coding agents like Claude Code® and Visual Studio® Code.

Data API Framework for AI Agents and Data Apps

Generative UI examples for: AG-UI, A2UI/Open-JSON-UI, and MCP Apps.