GitHub agents

Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.

AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage reservations, cancellations, and payments via the TourMind API.

Local-first multi-agent workspace for parallel sessions, tools, memory, workflows, desktop, and terminal.

AgentNet: Dynamically Graph Structure Selection for LLM-Based Multi-Agent System

A tool to interact with Windows drivers to perform a raw disk read and parse out target files without calling standard Windows file APIs

Autonomous, agentic, creative story writing system that incorporates stored embeddings and Knowledge Graphs.

A python code to interact with the GPT3 API to train the chatbot and use it.

AI image generation and editing via Gemini, OpenAI, Fal and Replicate, right in your WordPress media library. Native-like integration in Elementor, WooCommerce, and other plugins.

Build super simple end-to-end data & ETL pipelines for your vector databases and Generative AI applications

Distributed Multi-Agent Cooperation Algorithm based on MADDPG with prioritized batch data.

Rank LLMs, RAG systems, and prompts using automated head-to-head evaluation

Ballerina ReAct type Agent module using Large language models (LLMs)

jadx ai analysis plug-in

Build a keynote writing agent using CrewAI and watsonx.ai.

Official Code for "EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023)"

An md file as a chat interface and editable history in one.

An experiment that applies Google Research's `ReasoningBank` technique to Small Language Models. This experiment hopes to show that the same gains from the ReasoningBank paper also applies to much smaller, less capable models.

The open-source universal adapter for LLMs. Turn messy real-world data into clean, agent-ready context.

A virtual clinical environment for self‑evolving LLM diagnostic agents.

CLI built for AI agents to help navigate codebases better. An alternative to grep/find/glob

macOS accessibility inspector for AI-agent workflows. Hover, annotate, copy structured output.

Complete visual content system for Claude Code — 16 workflows, 2 AI models, aesthetic routing, and brand customization.

An open-source AI-powered frontend development platform built on DeepAgents and LangGraph. Generate complete React applications through natural language conversations.

Parameterized multi-agent orchestration framework for Claude Code and Gemini

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

AIRS-Bench: an AI Research Science benchmark for quantifying the end-to-end AI research abilities of LLM agents

Top papers related to LLM-based agent evaluation

English translation of MiroFish (github.com/666ghj/MiroFish) - A concise and universal swarm intelligence engine for predicting everything.

MCP server for AI assistants to read and manage Coros fitness data: sleep, HRV, daily metrics, activities, and structured workouts via the unofficial Coros API

基于SpringAI & alibaba框架进行大模型应用开发、Agent开发的示例工程

基于 LangGraph 和 FastAPI 的电商 AI Agent 框架。从 RAG 知识库到复杂的退货业务流的智能客服系统。

AI-powered assistant for EasyEDA — generate schematics from natural language, browse LCSC components, design PCBs with custom DRC configurations, and get interactive circuit design help.

专注于 VLM、VLA、世界模型及通用具身智能等方向，收录前沿论文、开源代码与数据集，追踪从感知到决策的下一代智能体技术。 A curated collection for multimodal intelligence research, covering VLMs, VLAs, World Models, and embodied AI — tracking next-generation agent technologies from perception to decision-making, with a focus on papers, code, and datasets.

AI驱动的系统性学术文献回顾工具 | AI-Powered Literature Survey Tool with 8-Phase Workflow & Agent Swarm Architecture

[ARCHIVED] Superseded by XenolithGraph — modern TypeScript/WebGL successor with React/Vue adapters and MCP for AI agents. See: github.com/XenolithEngine/xenolith-graph

Open-source AI-era employment platform connecting skills, jobs, enterprises, governance, and AI agents.

Alephant is an open-source AI Agent Gateway for routing, tracking, and controlling LLM usage across AI agents, members, and workflows, and for publishing agent capabilities as paid endpoints with x402 and MPP payment rails.

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

Animated components, blocks, charts, and templates for React. Copy them in, install with a CLI, or hand them to your coding agent.

The AI Agent designed for work with security in mind.

Markdown based AI agent memory with semantic search, hybrid retrieval, and offline-first sync between agents.

Experimental self-improving multi-agent coding system: a root agent recursively decomposes goals and delegates to specialist subagents, learning from failures by mutating a git-backed agent genome. Supports Claude, GPT, and Gemini.

An AI assistant that lives in your browser side panel

通用女仆机器人本地版 Rust 服务

A comic localizer built with python

A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.

An autonomous Site Reliability Engineering (SRE) and DevOps agent for Kubernetes with deterministic log analysis.

Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.

OpenCMO: An open-source, multi-agent AI Chief Marketing Officer built with OpenAI Agents SDK & Crawl4AI. Your BYOK alternative to $99/mo AI marketing agencies.

15-minute AI-agent positioning session for startups: forced choices, a sub-30-word statement, co-founder compile, and a 90-day proof plan. Claude Code / Cowork / Codex.

A Claude Code custom skill that turns Claude into a Tech Lead — coordinating parallel Worker Agents through a full dev workflow: PRD alignment, architecture, coding, QA, and PR review.

TerraMours实战项目，基于vue3.0+ts+naive UI+vite的ChatGPT项目前端。实现用户登陆和基于SK的多语言模型聊天、基于chatgpt和SD的多模型图片生成等功能。

Prototyping Generative AI Use Cases with Amazon Bedrock and Langchain

GPT-4 Vision Chrome Extension

使用Drl来解决多智能体卸载问题

Beginner-friendly repository for launching your first LLM API with Python, LangChain and FastAPI, using local models or the OpenAI API.

Academic Personal AI Infrastructure

Open efforts to implement ChatGPT-like models and beyond.

A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

LangChain Tutorial 3 动画演示透彻解释 Agent 概念 以及 实现Demo

📧 A drag and drop email editor using Next.js, Zustand and MUI

A curated list of awesome OpenAI's Whisper

Deeptoai 系列 RAG 教程

Mistral + Haystack: build RAG pipelines that rock 🤘

An MCP server that provides safe, read-only access to SQLite databases through Model Context Protocol (MCP). This server is built with the FastMCP framework, which enables LLMs to explore and query SQLite databases with built-in safety features and query validation.

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137 devices

A comprehensive GraphRAG (Graph Retrieval-Augmented Generation) system designed for biomedical research

An F/OSS solution combining AI with Wikipedia knowledge via a RAG pipeline

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

PI（π）—— When The Art of War Meets Cognitive Science for Ai

Pydantic AI agent that implements the idea of Claude Skills (progressive disclosure) with no reliance on Claude itself.

The NVIDIA NeMo Agent Toolkit UI streamlines interacting with NeMo Agent Toolkit workflows in an easy-to-use web application.

One prompt. A full AI engineering team. Go lie on the couch. 🧠

Zero-dependency JavaScript AI chat widget with SSE streaming, search, page context, accessibility, and theming.

Agent Skills for Claude Code and OpenCode

TradingAgents-A Share Edition` is a derivative open-source implementation based on [TradingAgents](https://github.com/TauricResearch/TradingAgents?tab=readme-ov-file), focused on China A-share research context and multi-agent collaborative decision workflows.

A lightweight, extensible Python framework for building and orchestrating single or multi-agent AI systems. | 一个轻量、可扩展的 Python 框架，用于构建和编排单智能体或多智能体 AI 系统。

OpenCMO: An open-source, multi-agent AI Chief Marketing Officer built with OpenAI Agents SDK & Crawl4AI. Your BYOK alternative to $99/mo AI marketing agencies.

人格蒸馏引擎 · 蒸馏自己看清自己，蒸馏亲友留住余温与回声 · Claude Code Skill

A personal AI agent that can work safely on your machine, remember useful context, and keep its data under your control.

A framework for self-improving prediction market trading agents.

OpenSRE — the memory-first AI SRE. Self-hosted incident investigation with episodic memory, knowledge graph, web console, Slack & Teams. opensre.in

Shared memory + orchestration for your coding agents — one MCP server, persistent vector memory, agent registry

On the path to fully autonomous agentic engineering

AI Engineering Specially Topics- Agentic AI & GenAI Explanation

AI coding agents forget. They forget across sessions, and they forget across tools. A decision you reached in Claude Code at midnight is invisible to Cursor the next morning. Honeycomb fixes that. Learn something once; recall it everywhere,

Local-first agent token usage audit dashboard

The official code implementation of the paper “Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration“.

给智能体安装了思维导图，让 Codex/Claude code/Agent 在复杂问题上用“可见思维树 + 轻量 MCTS”来探索，而不是线性瞎试。

Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Native macOS, bring-your-own-keys.

一个基于 LLM Wiki 的 Agent 知识库平台

Point your existing SDK at one URL and reach every LLM vendor — with real failover, not a try/except. One static Rust binary.

Open efforts to implement ChatGPT-like models and beyond.

A股 PEG 估值分析工具 — 彼得·林奇 PEG 投资法本地化实践 | A-share PEG valuation tool with AI-powered analysis

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

AI-powered data visualization assistant - Automatically generate professional charts from natural language descriptions. Supports 7 chart types and OpenAI/DeepSeek/Ollama platforms.