Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

autonomous agent with access to a tool library

High-fidelity, anycloud emulators running in your laptop. For DevOps programming, testing, and simulation.

A text-based user interface (TUI) client for interacting with MCP servers using Ollama. Features include agent mode, multi-server, model switching, streaming responses, tool management, human-in-the-l

Give any AI agent a full desktop — it sees the screen, clicks, types, and runs apps like a human. Automate anything with a UI: browsers, legacy software, internal tools. No API needed. One Docker comm

Cognithor - Agent OS: Local-first autonomous agent operating system. 16 LLM providers, 17 channels, 112+ MCP tools, 5-tier memory, A2A protocol, knowledge vault, voice, browser automation, Computer-us

Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and

An offline AI-powered video analysis tool with object detection (YOLO), image captioning (BLIP), speech transcription (Whisper), audio event detection (PANNs), and AI-generated summaries (LLMs via Oll

JRVS AI Agent with JARCORE autonomous coding engine - RAG knowledge base, web scraping, calendar, code generation. Powered by whatever local AI you choose.

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

Multi-agent memory consistency platform. We're hiring contributors—check HIRING.md

Tools to allow LLM clients to interact with Linux systems remotely

Official MCP Servers for AWS

A local sandbox for your AI agents

Self-hosted orchestration layer for autonomous AI agent teams. Shared memory, heartbeat scheduling, vault-first secrets, and cross-model peer review — one command to deploy.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta

A curated list of products, benchmarks, and research papers on autonomous code agents. Beyond coding — they're redefining how software changes the world.

It's YOUR data. Take it back. Get your Garmin Connect data into a local SQLite database and AI ready (MCP server)

See your agent think. Real-time observability dashboard for OpenClaw AI agents.

Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-instructions.

comprehensive Discord selfbot MCP server using discord.py-self

MaverickMCP - Personal Stock Analysis MCP Server

Open-Source Intelligent Command Layer

Unified framework for building enterprise RAG pipelines with small, specialized models

RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993

Official data.gouv.fr Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the French national Open Data platform, directly through conversation.

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

🛠️ Automate penetration testing with SploitGPT, an AI agent using Kali Linux tools for efficient security assessments and minimal user input.

Local First AI SEO Software on Nix, FastHTML & HTMX

89 skills and 38 specialized agents that enforce proven engineering practices for AI-assisted development. TDD, systematic debugging, parallel code review, and 10-gate development cycles — as a Claude

Assistant IA avancé (RAG, outils, Légifrance, OCR, skills, export de fichiers, historique) conçu principalement pour un usage avec AlbertAPI (DiNum)

Open-source multi-agent AI assistant powered by LangGraph, FastAPI & Next.js — 16+ agents, Human-in-the-Loop, MCP integration, voice TTS, RAG, 500+ metrics, 6 languages.

Security and best-practices scanner for AI Plugins, covering Codex, Claude, Opencode, Gemini & more. Scores trust for plugins 0-100.

arXiv MCP Server Client 🐙 enables AI assistants to search, retrieve, analyze, and summarize arXiv papers with features like author/category browsing, trends, and citation insights.

Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts

KiCAD MCP is a Model Context Protocol (MCP) implementation that enables Large Language Models (LLMs) like Claude to directly interact with KiCAD for printed circuit board design.

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.

Model Context Protocol (MCP) server for read-only interaction with NetBox data in LLMs

Agent memory and conflict detection platform. We're hiring contributors check HIRING.md

Local-first AI assistant — 9 specialized agents (code, web, debug, security…), 10M token vector memory, mobile relay via secure tunnel, real-time web search and document processing. Runs 100% on your

🤖 The most comprehensive directory of AI agent frameworks, platforms, tools, and resources - hundreds of curated entries covering open-source, no-code, enterprise, and autonomous solutions. NEW Boil

Security scanner for AI agents, MCP servers and agent skills.

📊 LLM Context Benchmarks - A comprehensive benchmarking tool for testing LLMs with varying context sizes using Ollama. Features dual benchmark modes (API/CLI), automatic hardware detection (optimiz

Claude Code plugin for Ruby, Rails, Grape, PostgreSQL, Redis, and Sidekiq development

Agentic AI assistant on Telegram, powered by Claude Code. Runs locally with shell access, spec-driven PR reviews, layered security, persistent memory, and scheduled jobs. Your machine, your data, your

🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.

Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

Autonomous VAPT platform. Give it a target (FQDN, IP, CIDR) — it hunts, it reports. Inspired by the Obsidian Order.

Your second brain, starting today. CLI + MCP server that helps you build, maintain, and search a knowledge vault that gets better every day. Works with any AI provider. Local-first, zero-prereq instal

Tool that just makes your open source project better using LLM agents

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

LLM proxy to observe and debug what your AI agents are doing.

YouTubeGPT is an LLM-based web-app that can be run locally and allows you to summarize and chat (Q&A) with YouTube videos.

Desktop AI Assistant powered by GPT-5, GPT-4, o1, o3, Gemini, Claude, Ollama, DeepSeek, Perplexity, Grok, Bielik, chat, vision, voice, RAG, image and video generation, agents, tools, MCP, plugins, spe

Local-first AI agent framework with GUI, memory, web search, personality constructs, speech i/o, tools, skills, CLI & Telegram features — fully self-hosted via Ollama.

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

🧠 Enhance AI conversations with Cognio, a persistent memory server that retains context and enables meaningful semantic search across sessions.

Open Framework for AI Agents to play Red Alert through Reinforcement Learning

[Community Supported] Perforce P4 MCP Server is a Model Context Protocol (MCP) server that integrates with the Perforce P4 version control system.

A MCP server to use StatCAN data

A Model Context Protocol server that provides task orchestration capabilities for AI assistants

PolyCouncil is an open-source multi-model deliberation engine for LM Studio. It runs multiple LLMs in parallel, gathers their answers, scores each response using a shared rubric, and produces a final,

CloneMe is an advanced AI platform that builds your digital twin—an AI that chats like you, remembers details, and supports multiple platforms. Customizable, memory-driven, and hot-reloadable, it's th

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

🧠 Enhance LLM agents with an agentic memory system, featuring automatic note construction, dynamic memory updates, and intelligent semantic retrieval.

A Model Context Protocol (MCP) server for Autodesk ShotGrid/Flow Production Tracking (FPT) with comprehensive CRUD operations and data management capabilities.

Universal LLM Gateway: One API, every LLM. OpenAI/Anthropic-compatible endpoints with multi-provider translation and intelligent load-balancing.

Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.

🔍 Enable local LLMs with real-time Google search, live feeds, OCR, and video insights using noapi-google-search-mcp server tools.

🔍 Implement hybrid search using Vespa and FastAPI, blending BM25 and dense semantic retrieval for efficient, accurate information retrieval.

🛒 Build a leading-edge e-commerce recommendation system using RAG architecture, Groq Llama 3, LangChain, and AstraDB, deployed on Kubernetes for scalability.

🚀 Build and scale reliable Retrieval-Augmented Generation (RAG) systems with this curated collection of tools, frameworks, and best practices.

Install your own AI DJ Being. She searches, downloads, listens, mixes, and generates music — autonomously. 30hrs for $0.04.

🔍 Enable AI-driven network security scanning with a production-ready Nmap MCP server supporting diverse tools, scan types, and timing templates.

⚡ Optimize vector searches with a hyper-efficient cache that uses machine learning for faster, smarter data access and reduced costs.

🛠 Remove watermarks from OpenAI Sora 2 videos using precise spectral analysis to keep video quality intact and watermark-free.

📄 Transform your workflow with persistent markdown files for planning, tracking progress, and storing knowledge like a pro.

🤖 Build your own local Retrieval-Augmented Generation system for private, offline AI memory without ongoing costs or data privacy concerns.

Local-first autonomous coding agent that plans, executes, validates, and finishes software tasks end-to-end.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

CLI for interacting with LangGraph API

Mustache for Python

The PEX packaging toolchain.

Google Cloud Artifact Registry API client library

AMQP 1.0 Client Library for Python

Scapy: interactive packet manipulation tool

Faster Whisper transcription with CTranslate2

Pulumi's Python SDK

Implements a fake file system that mocks the Python file system modules.

Community maintained hooks for PyInstaller

Kafka integration with asyncio

A modern Python package and dependency manager supporting the latest PEP standards

A library to identify devices (phones, tablets) and their capabilities by parsing browser user agent strings.

A set of tools, related to machine learning in production.

A small utility to modify the dynamic linker and RPATH of ELF executables.

Dynamic version generation

A wrapper around the pdftoppm and pdftocairo command line tools to convert PDF to a PIL Image list.

Microsoft Azure Azure File Share Storage Client Library for Python

CMake is an open-source, cross-platform family of tools designed to build, test and package software

Looker REST API

A refreshing functional take on deep learning, compatible with your favorite libraries

Ninja is a small build system with a focus on speed

Google Cloud Orchestration Airflow API client library

The backend—i.e. core services, APIs, and REST endpoints—to Jupyter web applications.

Human friendly output for text interfaces using Python

Google Cloud Workflows API client library

Library for building powerful interactive command lines in Python

HTTP/2-based RPC framework

Fast, Extensible Progress Meter

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge base