GitHub agents

Persona Control Language (PCL)

Local AI agent that audits URLs for SEO issues using Browser Use + Claude API + Playwright

MinusX is an Agentic Business Intelligence platform. It's Claude Code for data.

EFF-Monitoring是一款面向安全运营场景的告警协作与 AI 研判平台。平台围绕安全事件全生命周期，提供AI研判、处置流转、经验沉淀、插件接入等能力，通过证据驱动的分析与协同机制，帮助安全团队快速看懂告警、定位风险、联动上下游并提升处置效率。

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Agent Skill for Git workflow best practices - branching, commits, PR workflows | Claude Code compatible

Multi-LLM trading harness.

World's First 100% FREE Autonomous AI Employees Platform

一款开箱即用的 AI 智能客服系统，人工客服，客户转化

Patches Claude Code to show files read / commands run, and live streams thinking inline (optional) WITHOUT verbose mode.

OpenAI/Anthropic-compatible desktop proxy for Lingma and QoderCN, with Remote API, IPC fallback, tool emulation, image input, request logs, and model discovery.

Local-first AI agent for personal finance

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary Cobra CLIs with catalogs and generated Skills.

Automate web workflows on real browser tabs without hosting a browser farm.

🪼 A personal AI assistant that lives in Telegram — every topic is its own isolated Claude Code agent with layered persistent memory and proactive cron heartbeats. Open skeleton of a real, running system.

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

GitHub Copilot player agent customization pack for Slay the Spire 2 via STS2MCP

Open-source AI Agent platform with React/TSX & HTML plugin dev modes. Built-in 60+ APIs, multi-project, MCP tools, sandbox engine. Official + community-driven, building an extensible agent ecosystem for everyone.

Human-supervised AI code generation using Plan-Do-Check-Act methodology with TDD and refactoring. Works as Claude Code skill or standalone prompts.

Multimodal RAG system with CLIP/text embeddings, rank-fusion reranking, FastAPI serving, and Recall@5 evaluation.

AI-native tooling for robinhood integration

Simplified CloudTrail analysis for AI agents

Nakama is an open-source platform for building teams of AI agents. Every agent has a role. Together, they're your nakama.

AI Agent for Home Assistant

本地多 Agent 研发工作流控制台，支持 Codex、Claude CLI 与 Gemini 协同完成任务编排、执行监控和代码生成

A Spec-Driven Development (SDD) workflow definition repository using takt

Memory system for AI agents. #1 on LongMemEval — 96.2% (481/500). Beats every published system including Chronos, Mastra, Supermemory, and Emergence. Built solo in 16 days for $1,000.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

稳定、可控、业务驱动的企业级 AI Agent 低代码开发平台。

Recruit Codex (GPT) as an automatic adversarial reviewer inside Claude Code — diversity of thought, Claude has lead.

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

Slack AI Agent - a Slack app with MCP connections that can answer questions and perform agentic actions on Slack.

Agent skill for Google + Naver SEO on Next.js (Cursor & Claude Code)

Interactive data-flow diagrams your AI agent can write. One SKILL.md — install in Claude Code, Cursor, Codex, and 11+ other clients via `npx openskills install naorsabag/openhop`.

~967,000 live jobs from 16 ATS, enriched with LLM-extracted fields + embeddings, released CC0. Includes agent tooling to search them (hull -> learn -> rank).

Code for "Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems"

Eldercare runtime: risk-gated companion with reminders, anti-fraud, family escalation, and traceability

🦊 Anti-detection browser CLI powered by Camoufox — browse, screenshot, search, extract, crawl with C++ level fingerprint spoofing

A step by step implementation to build an agent that runs for week to complete a task and self improve.

Session memory for Claude Code. Auto-captures every session into a plain Obsidian markdown vault. Zero config. MIT. macOS + Linux.

免费接入Deepseek应用的性能太弱（如元宝），所以我干脆自己做了一个。Windows 桌面 AI 助手，多模型 LLM 接入，内置搜索、文件读写、代码编辑等 Agent 工具集，基于 pywebview + Python 构建。

AI浏览器 MCP Server — Windows 本地浏览器自动化 | 243 工具 | Cursor/Claude/Cline | Web Scraping · JS逆向 · CDP断点 · 指纹伪装 · 填表RPA | FBrowser CEF 内核 | MIT 开源

AI Agent驱动的Claude code 软件开发工作流框架 — 让AI Agent协作完成软件全流程开发。自动生成PRD、架构设计、源码、教程，实现"描述即交付"。

Kraivor is an AI-powered system that analyzes real-world codebases and simulates how they behave under production stress, failures, and scaling conditions.

A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

Git-native AI code provenance: records which AI agent wrote which line, signs each attribution with ed25519, stores it in your git history. Cross-agent (Claude Code, Cursor, Copilot, Codex, Windsurf, OpenCode, Gemini).

⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.

MIT license, Codex skill/plugin for source-first PowerPoint/PPTX generation: editable decks, style routing, data artifacts, and QA.

Frontier IDE built for AI coding.

Runtime authorization for AI agents — Node.js SDK

把 Claude Code 从'会用'推到'造得出'的实战知识库 + Agent Runtime 工坊

A security scanner for Agent Skill packages. Skill Sentinel uses multi-agent AI analysis to detect prompt injection, data exfiltration, command injection, malware, and other threats hiding in skill packages for Cursor, Claude Code, Codex, and OpenClaw.

Tool-agnostic 13-phase AI development pipeline — turns a task description into reviewed, committed code through automated design, adversarial review, security, test, and code-review gates. One bash engine, balanced Opus/Sonnet routing, self-healing commit review.

AgentPay-AI is a lightweight pay-per-use GenAI agent platform that simulates token-based billing (USDC-style) for AI tasks. It demonstrates how AI services can be monetized at the request level, similar to how real-world AI APIs charge users per token or request.

AuditAI is an Agentic AI-powered website auditing tool that analyzes SEO, performance, accessibility, and security issues using AI-generated insights.

A standalone, personality-driven multi-agent workspace application written in C, & C++

You put an agent into an Elpis, and it becomes Elpis; Be Elpis my friend.

A modern desktop IDE with AI-powered chat assistant, Monaco Editor, and integrated terminal.

One command to turn any codebase into an MCP server

移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台

Visual agent design platform for embodied AI — prototype agents as typed node graphs that execute against simulators in real time.

Floating traffic light for AI coding agents (know when your agent is idle, thinking, or writing)

用大白话讲透 AI 和 Agent，从 ChatGPT 到智能体，零基础也能看懂的工作指南。基于 WorkBuddy 多模型协作平台创作。使用求是skill作为主要技能。

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.

Benchmark and demo harness for measuring LLM agent tool-context budget tradeoffs.

Aprenda Inteligência Artificial do zero: fundamentos, prompt engineering, embeddings, RAG, agents, MCP e produção. Guia 4noobs da comunidade HE4RT.

The Semantic Time Machine & Orchestrator for AI-Generated Code.

Open Brain is a user-owned memory and continuity layer for coding agents. It stores provenance-aware semantic memory in PostgreSQL + pgvector, builds trusted context across sessions, and supports reviewed learning through REST, MCP, CLI, a dashboard, and adapters for Hermes, Medusa, Codex, and Claude Code.

Home Assistant Config as Code — manage HA with Python scripts + AI coding agents

基于 Golang 和 Cloudwego Eino 框架的 AI Agent 个人助手

Biomni-Web: A General-Purpose Biomedical AI Agent with Custom UI

工业液位与字符检测质量 Agent：集成 YOLO、液位反演、字符识别、受控复检、确定性仲裁、RAG 解释与 SQLite 审计。

The visual layer of your agent harness. Renders React components and Three.js scenes from source, with structure and evidence behind every frame — so agents can see, verify, and fix what they built.

CLI to use Fireworks AI models in Claude Code, Codex, OpenCode, Pi, and other coding agents.

AI-native construction estimating platform for intake, takeoff, pricing, scheduling, knowledge, and quotes.

Bilibili Video Notes 是一个从 B 站教育/讲课视频自动生成带截图的 DOCX 学习笔记的工具。它通过下载视频与 AI 字幕、全覆盖抽帧、OCR + 感知哈希去重、AI 视觉打分精选、提取图中关键内容，最终融合生成结构化的 DOCX 笔记。包括且不仅限于支持 Hermes Agent、Claude Code、Codex CLI 等多 Agent 直接调用，也支持任何 OpenAI 兼容格式的多模态视觉 API。可用于本地视频，适用于考研党等网课人群，帮助大家解放做笔记的双手，只需认真听课即可。

a toolkit for adding self-custodial bitcoin payments to applications and agents

A debugging framework for agentic AI systems: diagnose failures, attribute root causes, recover with evidence, and validate fixes through reruns.

Talk to anyone: /coach persona plugin for Claude Code — research any public figure from their YouTube + web, then talk to them

Agnes AI model integration skills for OpenAI-compatible text, image, video, and agent workflows.

Preserve knowledge, sustain wisdom forever.

Production agent skills for Claude Code, Cursor, and any SKILL.md harness — Codex fleets, video pipeline, monorepo review bundles, multi-chain explorer.

Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1.

Build beautiful games with high-quality 3D assets using Thrixel and Claude Code.

Interactive Sandboxes for AI Agent Evaluations & Reinforcement Learning on 3rd party APIs (Slack, Linear, Box, gCalendar)

从 AI Agent 对话中提炼真正的开发能力

Fullbleed PDF Engine - deterministic Python/Rust document generation for reports, invoices, accessible/print-ready PDF, and compiled VDP.

基于大模型的自动化数据分析工具，支持上传 Excel/CSV 数据，通过 AI Agent 自动规划和执行分析任务，生成带可视化的复盘报告。 项目说明：这是一个学习项目，在探索不同 Agent 架构模式的过程中，迭代了多个版本的循环实现。因此项目中包含了 5 种不同的 Agent 运行模式，每种模式代表了不同的设计思路和实现方式，便于学习和对比。

Fullstack platform for sharing AI Agent skills, built with TanStack Start, Tailwind, and TypeScript. Features Clerk auth, Firebase real-time data, PostHog analytics; + codebase reviewed by CodeRabbit.

A single CLI to keep your local repositories, AI agent skills, and MCP server configurations in sync.

为电影改AI影视而生，面向 Agent 的电影级画面 Prompt Skill，专门生成 HBO / 好莱坞质感的生图提示词与 LOOK 迁移、一致性方案

Fold is an Effect-native, provider-agnostic, isomorphic agent core with an optional opinionated coding agent, CLI, and TUI. It supports multiple model providers (including openai/anthropic-compatible and subscription-backed providers for Codex, Grok, and OpenCode Zen), subagents, and RLM-like orchestration patterns.

Local-first AI job-application agent: it tracks every application after you apply, explains failures with per-field evidence, and answers questions about your search — while its Chrome side panel fills real ATS forms (Greenhouse, Lever, Ashby, iCIMS, Workday). Your data and API key never leave your machine.

OpenAI-compatible proxy bridge for the FreeBuff free tier: multi-token pool, session/agent-run lifecycle, streamed chat completions. Docker + 9router ready.

Anti AI-Slop agent skill that makes your ai language model communicate and generate clear and concise writing, avoiding any sign of being AI-generated

Sandboxed Python environments with the uv workflow. Registry-only installs, read-only dependencies, and deny-by-default networking. Local-first. No SaaS account required.

Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

An intelligent shopping website that combines a multi-agent framework with personalized recommendation, interactive assistance, and product exploration.