GitHub agents

Native macOS menu-bar dashboard for AI subscription quotas, reset forecasts, local token costs, and provider status — Codex, Claude, Gemini, Grok, and more.

Installable Codex/AgentSkills workflow pack for dev, Agent/RAG, API/data, Office artifacts, research diagrams, and authorized security review.

Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector

Learn to evaluate AI products for production — 21 hands-on lessons on evals, metrics, fairness, agents, red teaming, and release decisions for working PMs.

Open-source, self-hosted knowledge backend for AI agents — hybrid search (vector + keyword), MCP server, 5 connectors, Docker-ready

This project implements a RAG pipeline using the LangGraph framework, designed for efficiently analyzing financial documents, specifically 10-K filings.

Tmux sidebar for vibe coding. Manage sessions and monitor agents at a glance

🗺️ Conversational AI agent that extracts unlimited business leads from Google Maps with automatic email enrichment. Chat with GPT-4o to find any business, anywhere. Built with n8n, Serper.dev, and Perplexity AI.

🦾 Bridge OpenClaw AI agents with physical servo robots — Python library for LOBOT LX bus servo control, motion teaching & playback

ServiceNow MCP server: 450+ tools and 26 AI capabilities for any AI (Claude, ChatGPT, Gemini, Cursor, Copilot). Multi-transport (stdio, SSE, HTTP), A2A, dynamic schema discovery, read-only by default. Free and source available. Part of the NowAIKit suite.

Autonomous robotics research with simulation feedback

O Trebuchet Framework é uma infraestrutura robusta para a criação, execução e orquestração de Agentes de IA autônomos, projetada especificamente para hardware local. Diferente de soluções que dependem exclusivamente de APIs na nuvem, o Trebuchet prioriza a privacidade e o desempenho local utilizando llama-cpp-python para inferência de LLMs e chroma

This repository contains the code and data of the WebMall benchmark for evaluating the capability of Web agents to find and compare product offers from multiple e-shops.

[CVPR2026] InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs

Agentic AI server in Rust. Multi-provider LLM routing, tool calling, RAG, MCP, multi-tenant workflows.

An Obsidian plugin that synchronizes selected Zotero full-text items with your vault in realtime, vectorizes them and lets you chat with your pdf documents.

Self-hosted AI code review that runs in CI and posts inline comments. 12 AI providers (Claude, GPT-4o, Gemini, Ollama, …), 5 git platforms (GitHub, GitLab, Bitbucket, Azure DevOps, Gitea). BYOK. Rust.

LLM-wiki: drop in papers/articles/notes, get a structured, interlinked, searchable wiki knowledge base. LLM-wiki：扔论文、丢笔记，自动生成交互链接、可搜索的个人wiki知识库。

AI 测试用例生成系统。基于 DeepSeek + 百炼部署的 RAG 知识库，包含需求分析、测试用例生成、智能运维助手、产品指南等内容

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

Audit your website content against canonical brand messaging and GEO target prompts. Emits an agent-actionable edit plan.

🔥 Alianhub — the open-source alternative to Jira, Linear, Monday & ClickUp. Manage tasks, sprints, docs, and triage, all in one modern workspace.

The full-stack open-source agentic ecosystem.

Personal knowledge base with hybrid search and read/write access for AI agents

Pre-indexed code knowledge graph via treesitter, enchanced query with RAG, MCP server, private and local storage. Agent ready.

Production-ready multi-agent starter kit for LangGraph — 7 patterns, 5 LLM providers, CLI scaffolder, MCP integration, and HTTP server with SSE streaming.

Agent Orchestration: MCP server enabling multi-agent collaboration with shared memory, task queue, resource locks, Cursor rules, and AGENTS.md workflows.

System-level security for LLM agents: fine-grained policy enforcement on tool calls to defend against indirect prompt injection

Salesforce Claude Code Framework: 🚀 17 specialized subagents, 55 domain skills, and 29 hooks for Salesforce development — Apex, LWC, SOQL, Flows, Visualforce, Aura, Agentforce, DevOps, and Security. Work across Claude Code and Cursor.

为 Python 后端工程师打造的 AI 实战教程：涵盖机器学习、深度学习、大模型应用，17个行业项目，跨平台支持（macOS/Linux/Windows）

# Manga-Autonoma (powered by nano-banana-2 and ChatGPT Images 2.0)　Autonomous AI 4-panel manga production system using Gemini API and OpenAi API. / Gemini APIとOpenAI APIを活用した、Nano Banana 2 and ChatGPT Images 2.0対応の完全自律型AI4コママンガ制作システム。

Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive modes.

🧠 AI Agent skills for LLMs and AI Agents - Claude, Codex, Cursor etc.

用于测试 LLM API token 输出速度的 CLI 工具 / A CLI tool to test LLM API token output speed

A production-ready full-stack system that combines semantic search with spatial proximity to retrieve and reason over geospatial documents.

EduAgent is an AI-driven educational platform leveraging LangGraph agents and RAG to convert static documents into dynamic, personalized tutoring environments. The system utilizes principles of active recall to automatically generate adaptive study plans, interactive quizzes, flashcards, and semantic mind maps from course materials.

Malaysian accounting skill for Claude Code. Process client documents into accrual-basis financial statements, working papers, and tax computations.

Zero-cost AI Chinese novel writing. 900K+ chars. 3 OpenClaw skills. ¥0 API spend.

The most comprehensive MCP server for Polymarket — 48 tools spanning direct trading, market discovery, smart money tracking, copy trading, backtesting, risk management, and portfolio optimization. Works with Claude Code, Cursor, or any MCP-compatible client.

Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing so agents understand your codebase structure, and policy enforcement for doc consistency.

Postman Agent Skills for AI coding agents. Sync collections, generate code, run tests, create mocks, publish docs, audit security, and analyze API readiness.

ClosedLoop.AI — The open-source workspace for team-based agentic software development.

Convai Desktop Pet is a fun desktop companion app that brings animated chibi-style characters to life on your screen. These little friends don't just sit there — they walk around, climb your windows, fall with gravity, and best of all, you can have real conversations with them using AI!

阿洛娜AI是一个以游戏《蔚蓝档案》（Blue Archive）中角色"阿洛娜"为原型打造的桌面AI助手。

AI-powered adaptive learning platform combining Knowledge Graphs, Local LLMs, and Bayesian skill tracking. Privacy-first RAG with KG-enhanced retrieval, IRT/BKT mastery modeling, and real-time assessment generation.

Capture a logged-in browser task once — replay it forever at zero LLM tokens. Local-first browser-automation MCP for Claude Code, Cursor & any MCP host; credentials never leave your machine.

20位天涯大神的多智能体决策系统，multi-agent team

Claude skill for FS25 mod development — answers verified against the game's own decompiled engine source (1,842 files). 1,413 classes, 119 MessageTypes, the mod sandbox, 30+ patterns, 20+ pitfalls. Works without a local decompile.

Full Mistral AI MCP server — OCR, Voxtral audio, Codestral FIM, durable workflows, document extraction — for Claude Code, Cursor, Windsurf, Zed, Mistral Connectors

Hermes Windows Native Guide — Agent + WebUI, no Docker, no WSL2

Control your local Claude Code (and other CLI coding agents) from your phone over Tailscale. Self-hosted, peer-to-peer, no cloud relay — your code, sessions, and API keys never leave your machine.

Tame your AI coding agents with natural language. Generate enforced guardrails (CLAUDE.md, hooks, settings) from a single command.

Model Context Protocol (MCP) server that dynamically fetches and serves official Flet resources to AI agents, including documentation, controls, packages, and ecosystem components.

A notification inbox solution for tmux, because things happen while you're not looking now. Put in the intray and check at your own pace. 🤖 📨 👨‍💻

A Codex skill for thermal-fluid mechanical engineering research, proposal development, technical writing, data analysis, presentations, and AI-assisted workflows.

AI-native design engine. Agents live inside the canvas — no switching, plug any MCP agent (Claude, Codex, Cursor). Design anything: pages, decks, motion, video. Open-source alternative to Figma & Claude Design.

The dependency bloodhound for AI coding agents. Free, no API keys.

Zero-dependency Go proxy for rotating free-tier AI API keys. No more 429s.

AI-powered personal finance skill — 75 tools across 7 extensions for banking (Plaid), trading (Alpaca), portfolio monitoring (IBKR), tax optimization, market intelligence, and social sentiment. Built for the Agent Skills Protocol, works with 40+ AI agents.

The open-source client-agnostic agent harness

A skill graph for design engineering: animation, transitions, taste, typography, color, components, anti-patterns.

Hands-on study companion for the Claude Certified Architect - Foundations (CCA-F) exam.

LangGraph pipeline that ingests raw markdown, compiles an Obsidian-style vault (wikilinks, backlinks, Index.md), optionally runs LLM authoring and semantic “See also” links, refreshes a local QMD index when enabled, and lints the vault.

一个基于 Spring Boot、React 和 FastAPI 的 AI 智慧医药系统，包含医药商城、管理后台、智能问诊、药品推荐、图片识别和运营分析等功能。

Zero trust network for governed agent-to-agent communication - discovery, engagement contracts, session governance, and auditable collaboration across organizational boundaries. Built on OpenZiti. A2A compatible.

MITM proxy for Windsurf IDE — replace the LLM backend with your own Anthropic API key

Put an AI agent on rails: mount a Burr state machine as an MCP server so the agent can only take the next allowed step, with every step recorded and replayable.

Pi extension for SpaceXAI Grok/X.com Subscriptions

🧩🏢 Frappe HR Forge is a local ERPNext/Frappe HRMS development project for building custom HR modules. It includes a Docker portal, a prepared Frappe app, custom HR DocTypes, workspace, roles, permissions, demo seed data, a Python 3.11 ML scaffold, ETL pipelines, cached data sources, and a roadmap for future HR recommendations and planning.

🏭 Production-grade multi-agent orchestration framework — 6 collaboration modes, 8 specialized tools, 4 execution paths. From simple chain-of-thought to LLM-driven deep clustering and dynamic workflows, one framework for every agent collaboration scenario.

A pure-skill, host-agnostic AI engineering harness: PRD → TRD → Plan → TDD → dual-agent review → archive. Works with Claude Code, Cursor & Codex. No MCP required.

論 — Ask multiple AI agents, get consensus. CLI tool for multi-agent design decisions. Currently supports Kiro, Claude Code, Copilot — more coming.

Spec-driven multi-agent orchestration plugin for Claude Code — 13 agents, 35 skills, per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.

A launch-control room for your local AI agents — block minifig crew, NASA-style GO/NO-GO board, real-time events from Claude Code hooks and agent logs. No cloud, no simulation.

Any brain, any agent. Package an AI agent's brain — persona, MCP stack, skills, memory, config — into one open, signed bundle and install it into any framework (OpenClaw, Hermes, Claude Code) in one click.

Self-hosted, open-source AI resume builder for software developers.

Autonomous AI Agent built on tinyloom

Chatbot-GPT, powered by OpenIM’s webhooks, seamlessly integrates with various messaging platforms. This tool enables private and group chats with bots, enhancing interactive communication. It delivers quick, automated responses, ideal for optimizing customer service and dynamic discussions, meeting diverse communication needs.

Self-hosted, OpenAI-compatible AI gateway for organizations — multi-provider (Azure/OpenAI/Anthropic/Gemini), revocable per-allocation credentials, usage & cost tracking, and an OpenAI Codex–ready /v1/responses endpoint.

Local-first Gmail + LinkedIn writing copilot (MV3 extension) powered by Claude. Dev beta with one-command installer.

Open, read-only MCP gateway over the Yochai knowledge graph of the Jewish textual tradition — for AI agents and developers.

Hashtag is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

Bodhi — a local-first desktop AI agent that actually does the work: it breaks down tasks, calls tools, streams every step live, and turns repeat work into automation. A Tauri shell over the Bamboo agent harness (Rust) and the Lotus UI (React).

Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.

Ready-to go claws (NVIDIA NemoClaw + OpenClaw) across multiple sectors. Run on your ibl.ai instance or anywhere else.

Developer toolkit for vibe coding AI apps on the ibl.ai platform. Scaffold a production-ready Next.js app with iblai-app-cli and the @iblai/iblai-js SDK: SSO auth, AI chat, profiles, notifications, and analytics wired up out of the box. Pre-built components, Claude Code skills, and a hosted backend at iblai.app. Deploy in minutes.

New Update X69X BOT V3 ✔️

A self-hosted household AI chat app built on OpenClaw — multiple conversations, multi-user family life, and long-term memory on your hardware.

Chrome extension wallet for user-owned AI API access

Delphi-native, MIT-licensed RAG + linter for Delphi/Pascal source code. Symbol-exact + fuzzy + tree-sitter lint. Pure Delphi at runtime.

One-command local AI/RAG installer for macOS (Metal): Dify, Open WebUI, Ollama, Weaviate/Qdrant, Postgres, Redis. 230 tests.

一个生活在手机里的智能体伙伴

Agentic scientific-computing platform: a reactive multi-agent team that orchestrates PINA physics-informed neural-network workflows via pydantic-graph, with MLflow tracing/provenance and a marimo chat UI (plus A2A & AG-UI servers).

A local memory and coordination layer for anything that can make an HTTP request — agents, devices, sensors, and humans on one network. Sovereign, local, no cloud.

Make Claude Code sessions portable: share them with friends and teammates, or resume them on any machine.

An Express and AI SDK agent that triages new GitHub issues on Vercel, applying labels and a maintainer reply.

Daily curated arXiv papers on LLM agent simulation, multi-agent systems, city/society simulation, and agent training & alignment. Auto-updated feed classified by Claude.

AI-powered PR reviews running in your Cloud. Your models, your cloud, your rules. No code stored.

The Analytics Database for Agentic AI — Free for Personal Use