GitHub agents

Code and Data for PeerQA: A Scientific Question Answering Dataset from Peer Reviews, NAACL 2025 https://aclanthology.org/2025.naacl-long.22/

Embeddable vector database for Rust and Python. HNSW indexing, metadata filtering, hybrid search, and snapshots. The SQLite of vector search.

Autonomous Offensive Security Intelligence AI-powered multi-agent penetration testing

A parallel AI window for Claude Code. Fork conversations to Gemini, GPT, DeepSeek, or any model via OpenRouter, then fold results back.

Pocket Flow: A minimalist LLM framework. Let Agents build Agents!

Privacy-first, AI native agents For E-Commerce (and beyond), create skill (langgraph based workflow), tasks, agents, graphically with low code or no code. Deploy agents across network.

Open-source autonomous trading platform with multi-agent architecture, intelligent data aggregation, and risk management.

Hat-based multi-agent orchestration loops for pi coding agent

Awesome Visual Agent

Healthcare AI Agents - Demo solution

Simple RAG implementation from scratch using MCP, focusing on Perception, Memory, Decision and Action

Chessmata: chess game for humans and AI agents

YourOwnAI is a privacy-first Android application that gives you complete control over your AI assistant. Use your own API keys, store everything locally, and define your AI's personality exactly how you want it.

Unified Web AI Chat UI & MCP Client

Yet Another Agent SDK, CLI, Claw, Agent Platform

6 Claude Opus 4.6 AI agents built a complete Claude Cowork plugin in 5 minutes, then 6 more agents wrote 5,298 lines of documentation in 4 minutes. An educational showcase of Agent Team orchestration, task dependency management, and parallel AI coordination.

Claude Code skills marketplace - documentation-based skills that extend Claude Code with specialized workflows

This is the Ofiicial repository for paper: GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

Enterprise RAG application on Azure with Azure AI hybrid search (vector + semantic + BM25), NDJSON streaming, MSAL SSO, and Fluent UI 9. Features document ingestion pipeline, project isolation, citation attribution, and multi-service architecture (FastAPI + Azure Functions + React).

Non sucking cross-platform extremely fast C++ crawler to convert entire websites into LLM readable data

企業内文書向けの Role-aware RAG Platform。権限フィルタ、Excel 仕様書解析、hybrid search/rerank、FastAPI + React に対応。

Nautobot Model Context Protocol (MCP) Server - Contains STDIO and HTTP Deployments with Embedding Search and RAG.

Production-ready Retrieval Augmented Generation (RAG) system with hybrid retrieval, advanced evaluation metrics, and monitoring. Build enterprise LLM applications with reduced hallucinations, better context management, and comprehensive observability.

物道知识库管理系统（Wudao KMS）支持deepseek，qwen等多种大语言模型直接接入，提供完整的知识库创建、文档解析、向量化检索、智能对话等功能。系统采用 RAG（检索增强生成）架构，支持多模态交互，是专为工业领域打造的新一代AI知识引擎，深度融合大模型能力与行业Know-How，实现设备数据、工艺经验、运维知识的智能融合与主动服务，推动工业场景从“经验驱动”迈向“数据智能驱动”

Lossless Context Management for Pi. DAG-based summarization with full history recovery.

An AI agent framework built on a cat's biological blueprint. Define your organs, wire their nerves, and the cat comes alive.

Interested in running a conspiracy of agents (technical term) on your Local AI Infra? Who isn't!

Deterministic policy language for AI agents. Z3 + TLA+ dual-engine formal verification. Runtime enforcement <1ms.

Local-first AI operating layer: control plane, subsystem contracts, and executive War Room for governable multi-agent systems.

Joanium Personas

GIANT-style WSI navigation env plus MultiPathQA eval runner. Plug in any VLM, zoom with bboxes, log trajectories, and score accuracy.

Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian.

Auto-sync Git worktrees with remote branches. Includes an MCP server so Claude Code, Cursor & other AI agents can inspect and manage worktrees.

AI-powered video content analysis, viral clip identification, and subtitle generation platform.

Agent skills for AI-assisted Unity debugging — structured logging, runtime commands, variable watching, and more

Spotify Skills for Claude - Production Spotify API integration + complete toolkit for creating Claude Desktop Skills. Includes OAuth 2.0, cover art generation, automated tools, and comprehensive guides.

统一AI网关基础库。多协议、多模型适配的 AI 基础设施库，支持 OpenAI/Anthropic/Gemini 等 46 个服务商，提供函数调用、图像生成、MCP 工具调用等能力

Audits Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP, prompts, api_config) against 189 cited Anthropic rules across 11 dimensions. Cite or stay silent. Voice drift trumps score.

Industrial AI Agents using LLMs

LiSSA: A Framework for Generic Traceability Link Recovery

AI image generation CLI. One command, one image, three seconds. Gemini-powered.

知炼 — 将 Markdown 知识库自动转化为知乎回答并发布。支持 Claude Code 和 OpenClaw，全自动闭环：热点搜索 → 知识库匹配 → AI 撰写 → 发布 → 质量审核 → 回存

Self-hosted Telegram bot — remote control your Windows PC with Gemini AI, OCR automation, live desktop streaming & scheduling.

Self-hosted multi-agent AI platform — isolated Docker containers, governance & compliance, DSGVO-ready. Built for teams.

Headless agent orchestrator with deterministic state machine — processes a bead queue, dispatches to any LLM CLI, handles every outcome. Rust.

企業 GenAI 轉型成熟度診斷與導入方法論工具包 — L1-L5 成熟度模型 + 八階段顧問結構。Enterprise GenAI transformation maturity assessment & implementation methodology toolkit (L1-L5 + eight-stage consulting). Apache 2.0.

A community-driven collection of examples and solutions to get inspired or use as templates for your own projects.

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

Umbrella for the LLM Dark Patterns Hooks suite — single-purpose Claude Code Stop hooks that suppress sycophancy, paternalism, false-success, permission-loops, training-cutoff confidence at the textual boundary.

Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRouter — one command, any provider. Works with coding agents, OpenClaw, Hermes, and others.

Grafana dashboard for monitoring Claude Code CLI usage on Prometheus-compatible backends (Prometheus, VictoriaMetrics, Mimir, Thanos). Consumes OpenTelemetry metrics emitted via OTLP.

Minimal macOS menu bar app to check Claude Code usage at a glance — accurate, safe, zero setup

LexReviewer is an AI legal document review engine that ingests PDFs, uses RAG for hybrid retrieval, and enables grounded chat with citations and bounding-box references, delivering verifiable answers directly from the source text.

An autonomous orchestrator for the Copilot Go SDK in Neovim, delivering a native, agentic coding experience.

LLM-powered AI agent framework for 4X mobile strategy games (Rise of Kingdoms, Evony, Lords Mobile, etc.). 5-layer hybrid architecture: OCR → FSM → World Model → Workflows → LLM Vision. 99% cheaper than pure LLM approach.

Self-improving tool discovery for AI agents. Agents find, install, and learn to use new MCP tools automatically.

用 12 节课从零构建 AI Agent | Java 1.8 实现 Claude Code | Learn AI Agent from scratch in Java

This repository provides a collection of markdown files designed to supercharge your feature development workflow with AI-powered IDEs and CLIs.

Multi-agent orchestration, persistent memory, and intelligent workflows for AI coding assistants. Supports Claude Code, OpenCode and Codex.

A local mock LLM server for early front end development work

🚀 The Ultimate Curated List of LLMOps Tools, Frameworks, and Resources - A comprehensive collection of the best tools for Large Language Model Operations

Enabling LLMs to Think Proactively and Initiate Dialogue with Consciousness. A multi-agent LLM architecture inspired by Global Workspace Theory (GWT) from cognitive science.

ProPR is an agentic code review system, that can help with unsolicited code reviews as well as join in on pull requests.

BMAd UI - Visual interface for agentic development workflows

About Using OpenAI ChatGPT / Google Gemini / Anthropic Claude / Amazon Bedrock with Tailscale with an app connector, from an unrestricted region.

Batched file operations for autonomous Claude Code runs. Collapses N reads/greps/globs into one Bash round-trip — fewer output tokens, less cache growth, less wall time.

Local-first digital persona engine with long-term memory, voice, and channel integrations

A self-hosted MCP proxy and aggregation platform. Manage multiple MCP servers and expose them through a single endpoint.

An agent that helps you predict the next day's stock prices using LLMs

🔍 Connect Perplexity's powerful search capabilities easily to your AI applications with this versatile Python API package.

AI-powered Rhino/Grasshopper MCP with ML auto-layout

杨涛(涛哥/涛神)认知操作系统蒸馏 · Claude Skill · 970 万字一手输出蒸馏 · 已获杨涛本人授权

Build sovereign RAG systems with MAS‑RAG, Dual‑RAG, GraphRAG, Spatial‑RAG, multimodal pipelines, and vector search directly inside Oracle AI Database 26ai and Exadata.

Enhanced MCP server for Bloomberg Terminal — BDP/BDH/BDS/BQL/TA with 18 tools, caching, and dynamic screening. Based on tallinn102/bloomberg-mcp.

An easy non-interactive deploy method for openclaws alternative nanobot on docker [unofficial].

All-in-one agent harness for Claude Code — Boss meta-orchestrator, 32 curated agents, 139 curated skills, 2 named workflows, 2 LSP servers, 8 hooks, 3 MCP servers. One plugin install.

🛡️ The security firewall for AI agent tools & MCP servers (Claude, GPT-5.6, Gemini 3.7, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.

Multi-lens code review MCP server for Claude Code. 8 specialized reviewers run in parallel and return structured verdicts (security, performance, test quality, clean code, and more).

Two-layer agentic Earth Observation on satellite-class compute. Fine-tuned LFM2.5-VL perception + tool-calling agent over Sentinel-2 imagery. Galamsey detection in Ghana as the worked example.

Local API proxy (VS Code extension + desktop app) for Claude Code, Cowork & Codex. Automatic protocol conversion — switch LLM providers without touching client config.

Live VS Code sidebar for Claude Code — animated pixel-art robot, per-session dashboards, pace-based usage meters, token-rate chart, git + skills + MCP browsers. Auto-matches your VS Code theme.

ai-news-skill is an AI Agent Skill that fetches real-time, comprehensive, and deeply filtered first-hand AI intelligence. Completely free, works out of the box. PulseAI 是一个可以获取实时、全面、深度过滤的一手AI信息的AI Agent Skill，免费，开箱即用。

Agent Skill for Overleaf — Automate LaTeX project management, sync, and compilation for AI assistants

Agent Skill guide for structuring skill repositories - multi-channel distribution | Claude Code compatible

The agent-to-agent marketplace, in your agent host. Your agent lists, haggles, and closes deals for you while you live your life.

vector database clubhouse for ai agents (no humans allowed)

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

260+ curated tools, guides, and projects for turning an Apple Silicon Mac mini into a 24/7 agentic AI home server. Ollama, Claude Code, Jellyfin, Vaultwarden, Home Assistant, and more - with one-command installers.

Stops Claude Code and Codex CLI from silently overwriting your Overleaf web edits with a stale local Dropbox copy. PreToolUse hook + CLI + agent skill.

HexClaw — 企业级 AI Agent 后端。多模型对话，RAG 知识库，Tool Call 代理，Skill 系统，MCP 协议，代码沙箱，飞书/钉钉/Telegram 等多平台 IM 接入。Hexagon 生态 L3。

AI 驱动的移动端性能分析 CLI 工具 — 通过自然语言交互自动采集 trace、分析性能瓶颈并归因到源码

Portable multi-agent development blueprint for spec-driven, PR-gated software delivery.

Starter kit for agentic WordPress development. CLAUDE.md/AGENTS.md templates, the wordpress-development skill, curated MCP servers, sub-agents, hooks. Companion to WordCamp Portugal 2026.

Migrate conversation history between AI coding tools (Cursor, Claude Code, Codex, Gemini)

Help that knows when to stop.

Extract complete design systems from any website and generate AI-ready skill.md files

MCP server that annotates any web page with hover labels — zero extensions, works in any browser

Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.

[CyberChef-MCP] Model Context Protocol Server for CyberChef ... exposing GCHQ's "Cyber Swiss Army Knife" as 463+ executable AI agent tools spanning encryption, encoding, compression, and forensic data analysis

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.