Facebook Business SDK

One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when

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

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

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compou

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring. Your agent teaches itself new

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligen

Persistent memory for AI coding agents. Cross-session context, global knowledge, and autonomous task execution.

NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust scoring, 150+ MCP tools. Works with Claude Code, Codex, Claude Desktop & any MC

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

Graph RAG with pure vector search, achieving SOTA performance in multi-hop reasoning scenarios.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, R

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

LlamaIndex is the leading document agent and OCR platform

Build AI agents that actually do things. Synapse is an open-source platform for creating, connecting, and orchestrating AI agents powered by any LLM — local or cloud.

Your AI assistant that never forgets and runs 100% privately on your computer. Leave it on 24/7 - it learns your preferences, helps with code, manages your health goals, searches the web, and connects

Memori is agent-native memory infrastructure. A SQL-native, LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.

Seedance 2.0 Shot Design Skills

SRE Agent - CNCF Sandbox Project

Declarative Agent Orchestration. Ship while you sleep.

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI),

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

The conversational control layer for customer-facing AI agents - Parlant is a context-engineering framework optimized for controlling customer interactions.

Agent Zero AI framework

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

Secure AI conversations with documents, video, audio, and more. Personal workspaces for focused context, group spaces for shared insight. Classify docs, reuse prompts, and extend with modular features

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

Buddhist Digital Text Platform — 9,200+ texts, 500+ sources, 8 UI languages, AI Q&A (RAG), knowledge graph, full-text search

A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code

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

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Harness LLMs with Multi-Agent Programming

"RAG-Anything: All-in-One RAG Framework"

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.

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Ultra-Lightweight, Pure Python Multimodal Agent.

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

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

A thin cython wrapper around llama.cpp, whisper.cpp and stable-diffusion.cpp

Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cur

Conversational & memory-enabled AI research partner for multi-omics analysis. From biological idea to full research paper.

Framework for AI agents to build and maintain an Obsidian wiki using Karpathy's LLM Wiki pattern

Describe it or draw it. Kiln makes it real. — 461 MCP tools for AI-agent-controlled 3D printing. OctoPrint, Moonraker, Bambu Lab, Prusa Link, and Elegoo.

Agentic RAG R1 Framework via Reinforcement Learning

One API for 20+ LLM providers, your databases, and your files — self-hosted, open-source AI gateway with RAG, voice, and guardrails.

Self-evolving deep research system for Claude Code. Zero API keys.

Markdown-first work-memory protocol for existing agents, with maintained knowledge, candidate notes, evals, and an example KB.

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

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

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Cop

Shell and coding agent on mcp clients

Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing

Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

A sovereign cognitive architecture with IIT 4.0 integrated information, residual-stream affective steering (CAA), Global Workspace Theory, active inference, and 72 consciousness modules — running loca

Create a plan from a description in minutes

Curated list of the best truly open-source AI projects, models, tools, and infrastructure.

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

The Next-Gen Agent-Native Skill Recommendation Engine

META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡

This project implements a comprehensive framework for Knowledge Graph Retrieval Augmented Generation (KG-RAG). It focuses on financial data from SEC 10-Q filings and explores how knowledge graphs can

AI travel planner with 7 specialized agents, RAG, and tool-calling. Built with CrewAI & LangChain. Generates personalized itineraries with flights, hotels, activities, and cultural tips. Production-re

A lightweight AI agent framework for vertical domain applications | 面向垂域应用的轻量级 AI Agent 框架

Local-first Agentic Memory Layer for MCP Agents • 25 tools • Hybrid search (FTS5 + vector + MMR) • GDPR • 100% local

A flexible multi-interface AI agent framework for building agents with reasoning, tool use, memory, deep research, blockchain interaction, MCP, and agents-as-a-service.

Claude Code skills, architectural principles, and alternative approaches for AI-assisted development

One memory layer for every AI agent. Local-first, markdown source of truth, and CLI/HTTP/MCP native. Your agent forgot who you are. Again. Dory fixes that.

The LLM Evaluation Framework

Project Infinity leverages MCP and Graph RAG to turn LLMs into a professional D&D 5e Game Master, governed by a dedicated dice server and a persistent player database for a truly consistent adventure.

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

Ambient intelligence that sees what you see, hears what you hear, and acts on your behalf

Open-Sable is a local-first autonomous agent framework with AGI-inspired cognitive subsystems (goals, memory, metacognition, tool use). It can run continuously on your machine, integrate with chat int

A self-improving AI agent that learns from experience. Runs entirely on a local 9B model. Security by absence — dangerous capabilities were never built.

A tool that compiles messy natural language prompts into a structured intermediate representation (IR) and optionally sends them to LLMs like ChatGPT for cleaner, more reliable responses.

Autonomous AI agent that researches viral content, generates posts, publishes them, measures engagement — and rewrites its own strategy based on what worked. Self-learning loop powered by LangGraph +

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

🧠 Transform documentation chaos into a structured memory system with Mnemos, your self-hosted, multi-context knowledge server for developers.

AI co-pilot for ComfyUI — 113 tools for workflow authoring, model provisioning, and iterative rendering. Multi-provider (Claude, GPT-4o, Gemini, Ollama). Ships as MCP server or standalone CLI.

Second Brain is a desktop application that acts as a personal knowledge base, using retrieval-augmented generation (RAG), multimodal AI models, and a hybrid lexical/semantic search algorithm to intera

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

🍀 Self-hosted multi-agent AI orchestrator — chat with Claude, Gemini & Copilot CLI from Telegram, WebEx, or browser. 5 runtimes, 17+ models, task scheduling, skill plugins.

🤖 Build a smart AI assistant that learns from any website using a Retrieval-Augmented Generation framework with local models powered by Ollama.

Workspace Architect is a zero-friction CLI tool that provides curated collections of specialized agents, instructions, and prompts to supercharge your GitHub Copilot experience.

Python LLM-RAG deep agent using LangChain, LangGraph and LangSmith built on Quart web microframework and served using Hypercorn ASGI and WSGI web server.

Broken RAG For The Broken Souls

🤖 Transform internal knowledge retrieval with a secure, on-premise RAG-powered chatbot that enhances efficiency through natural language queries.

Self-hosted autonomous AI agent — 9-layer cascade, Docker sandbox, encrypted vault, review/build/control plane, 1407+ tests

Turn AI into a persistent, memory-powered collaborator. Universal MCP Server (supports HTTP, STDIO, and WebSocket) enabling cross-platform AI memory, multi-agent coordination, and context sharing. Bui

The Eternego codebase

Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.

Provide a local, privacy-focused AI assistant for Telegram that runs fully on your machine without sending data to the cloud.

🎶 Enhance audio quality with ComfyUI-AudioSR, a versatile tool for upscaling sounds to 48kHz for better clarity and listening experience.

Provide open-source AI bots for Lark to automate tasks like brainstorming, project planning, content creation, and monitoring within a secure chat interface.

🔍 Automate penetration testing with an intelligent agent that organizes security assessments, leveraging local LLMs and Kali Linux for effective exploitation.

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

Hybrid cloud-local AI Employee that runs 24/7 on a cloud VM, monitors Gmail/WhatsApp, drafts responses, and queues approvals via git-synced Obsidian vault. Human-in-the-loop safety gates for email, so

🤖 Generate tailored AI training datasets quickly and easily, transforming your domain knowledge into essential training data for model fine-tuning.

🧠 Build an offline RAG chatbot to answer questions from PDFs, adapting responses based on user experience levels with a smooth chat interface.

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

Enable peer-to-peer collaboration between AI agents with human supervision for complex task coordination and decision-making.

🤖 Create and modify workflows effortlessly with ComfyUI's AI assistant, enabling natural conversations with agents like Claude and Gemini.

🎥 Generate AI-driven videos with Seedance 2.0, offering precise physics, lip-sync, and prompt accuracy for seamless content creation.

🤖 Build intelligent, offline LLM agents with LangGraph and llama-cpp-python using this starter template for local, private tool-calling applications.

Protect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.

No description

🚀 Explore high-quality skills for SpoonOS, Web3, AI productivity, and enterprise tooling with 57+ curated Python scripts across multiple challenge tracks.

Efficient Retrieval Augmentation and Generation Framework

A structured reasoning and decision architecture for stable, interpretable, and hallucination‑resistant AI systems. An open standard for human–AI collaboration and autonomous systems.