The Open Source Directory That Did Its Homework

Find what's already been built before you build it. 83 projects in the catalog.

DeepScientist

ResearAI

A Safe

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

#ai-agents#research#workflow-automation#multi-agent+8
1.3k1145
TypeScript

cronflow

dali-benothmen

A Safe

High-performance, code-first workflow automation engine. TypeScript-native with Rust core for enterprise-grade speed, efficiency, and developer experience.

#workflow-automation#framework#library#real-time+6
10395
Rust

ida-pro-mcp

mrexodia

A Safe

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

#mcp#server#plugin#ai-agents+6
7.1k8625
Python

eliza

elizaos

A Safe

Autonomous agents for everyone

#ai-agents#multi-agent#framework#llm+11
18.1k5.5k5
Rust

LEANN

yichuan-w

A Safe

[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

#rag#vector-database#embeddings#local-first+10
10.6k9285
Python

Awesome-finance-skills

RKiding

A Safe

A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills

#ai-agents#llm#plugin#rag+9
1.6k2005
Python

agentscope-runtime

agentscope-ai

A Safe

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.

#ai-agents#framework#server#docker+10
7011385
Python

autoresearch

uditgoenka

A Safe

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

#ai-agents#workflow-automation#code-generation#prompt-management+8
3.1k2345
Shell

supabase

supabase

A Safe

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

#database#auth#api#real-time+6
100.1k12k5
TypeScript

ST3GG

elder-plinius

B Good

All-in-one steganography suite

#security#cli-tool#library#server+10
8542115
HTML

beautiful-mermaid

lukilabs

A Safe

beautiful-mermaid is a TypeScript library for rendering Mermaid diagram syntax into beautiful SVG output or ASCII/Unicode art. It operates entirely synchronously with zero DOM dependencies, supports 6 diagram types (flowcharts, state, sequence, class, ER, and XY charts), ships with 15 built-in themes, and provides full Shiki VS Code theme compatibility. Designed for AI-assisted programming workflows and terminal environments, it can run in browsers, Node.js, React, and CLI tools without requiring a headless browser or async rendering pipeline.

#library#code-generation#ui-components#ai-agents+4
8.6k2665
TypeScript

codebase-to-course

zarazhangrui

A Safe

A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

#ai-agents#context-engineering#prompt-management#code-generation+3
3k2825
CSS

pretext

chenglou

A Safe

Pretext is a pure JavaScript/TypeScript library for fast, accurate multiline text measurement and layout without triggering DOM reflow. It implements its own text measurement logic using the browser's canvas font engine, providing precise paragraph height calculation, line segmentation, and bi-directional (bidi) text support across all languages and emoji. It offers two main use-case APIs: a simple prepare/layout pair for height measurement only, and a richer prepareWithSegments set for manual line-by-line layout enabling rendering to Canvas, SVG, WebGL, or server-side contexts. An experimental inline-flow sidecar handles mixed inline runs with atomic items and boundary whitespace collapse.

#library#ui-components#real-time#local-first
35.3k1.8k31
TypeScript

dub

dubinc

A Safe

The modern link attribution platform. Loved by world-class marketing teams like Framer, Perplexity, Superhuman, Twilio, Buffer and more.

#analytics#api#payments#auth+6
23.3k2.9k5
TypeScript

OpenBB

OpenBB-finance

A Safe

Financial data platform for analysts, quants and AI agents.

#api#data#library#cli-tool+8
65.2k6.4k5
Python

gstack

garrytan

A Safe

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

#ai-agents#code-generation#workflow-automation#context-engineering+9
62.6k8.4k5
TypeScript

timesfm

google-research

A Safe

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

#library#research#ai-agents#llm+5
13.6k1.2k5
Python

itshover

itshover

A Safe

Icons that move with intent

#ui-components#library#template
1.7k1132
TypeScript

LightRAG

HKUDS

A Safe

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

#rag#knowledge-graph#llm#framework+8
31.7k4.5k1
Python

omlx

jundot

A Safe

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

#llm#server#self-hosted#local-first+10
8.2k6825
Python

inngest

inngest

A Safe

The leading workflow orchestration platform. Run stateful step functions and AI workflows on serverless, servers, or the edge.

#workflow-automation#multi-agent#server#cli-tool+6
5.1k2783
Go

agentscope

agentscope-ai

A Safe

Build and run agents you can see, understand and trust.

#ai-agents#multi-agent#llm#framework+9
22.8k2.3k5
Python

judge0

judge0

A Safe

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

#server#api#code-generation#evaluation+6
4.1k8375
HTML

phantom

ghostwright

A Safe

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

#ai-agents#multi-agent#mcp#memory+10
9481015
TypeScript

VibeVoice

microsoft

A Safe

Open-Source Frontier Voice AI

#voice#llm#streaming#fine-tuning+4
34.9k4k1
Python

TradingAgents

TauricResearch

A Safe

TradingAgents: Multi-Agents LLM Financial Trading Framework

#multi-agent#ai-agents#llm#framework+6
46k8.3k21
Python

godogen

htdt

A Safe

Claude Code skills that build complete Godot 4 projects from a game description

#code-generation#ai-agents#workflow-automation#llm+4
2.5k2261
Python

markitdown

microsoft

A Safe

Python tool for converting files and office documents to Markdown.

#library#cli-tool#llm#rag+5
93.1k5.6k2
Python

awesome-finance-skills

rkiding

A Safe

A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills

#ai-agents#llm#plugin#framework+4
1.5k198
Python

claw-code

ultraworkers

B Good

[Notice] The repo temporarily locked while ownership transfer. in the meantime we maintain on here: https://github.com/ultraworkers/claw-code-parity. The fastest repo in history to surpass 100K stars ⭐. Better Harness Tools that make real things done. Built in Rust using oh-my-codex.

#ai-agents#cli-tool#mcp#framework+3
134.8k101.7k1
Rust

emdash

emdash-cms

A Safe

EmDash is a full-stack TypeScript CMS built on Astro and Cloudflare (D1, R2, Workers). It reimagines WordPress-style content management with sandboxed plugin execution via Cloudflare Dynamic Worker isolates, structured content via Portable Text, passkey-first authentication, a built-in MCP server for AI tool integration, and portable database/storage abstractions supporting SQLite, PostgreSQL, S3-compatible storage, and more.

#framework#mcp#cms#self-hosted+7
2.5k1535
TypeScript

skyclaw

nagisanzenin

A Safe

Radically Innovative AI Agent. Free and Open Source Forever.

#ai-agents#llm#multi-agent#computer-use+11
387845
Rust

clawvault

Versatly

B Good

🐘 An elephant never forgets. Structured memory system for AI agents.

#memory#ai-agents#knowledge-graph#rag+6
634602
TypeScript

kavach

LucidAkshay

A Safe

Tactical AI Workspace Monitor & EDR

#security#ai-agents#desktop-app#llm+3
234422
TypeScript

code-review-graph

tirth8205

A Safe

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

#knowledge-graph#mcp#code-generation#llm+8
3.9k3453
Python

local-talking-llm

vndee

A Safe

A talking LLM that runs on your own computer without needing the internet.

#llm#voice#local-first#ai-agents+3
8261793
Python

cutter

rizinorg

A Safe

Free and Open Source Reverse Engineering Platform powered by rizin

#security#desktop-app#plugin#cli-tool
18.6k1.3k3
C++

OpenJarvis

open-jarvis

A Safe

Personal AI, On Personal Devices

#ai-agents#llm#framework#local-first+6
2k3625
Python

MiroFish

666ghj

A Safe

A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物

#multi-agent#ai-agents#llm#knowledge-graph+6
47.5k6.8k4
Python

MiroShark

aaronjmars

A Safe

Universal Swarm Intelligence Engine

#multi-agent#ai-agents#llm#knowledge-graph+10
384625
Python

GitNexus

abhigyanpatwari

A Safe

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration

#ai-agents#browser-extension#cli-tool#code-generation+9
21.1k2.4k5
TypeScript

chops

Shpigford

A Safe

Your AI agent skills, finally organized. A macOS app to browse, edit, and manage skills across Claude Code, Cursor, Codex, Windsurf, and Amp.

#desktop-app#ai-agents#prompt-management#llm+4
1.1k605
Swift

Claude-Code-Game-Studios

Donchitos

A Safe

Turn Claude Code into a full game dev studio — 48 AI agents, 36 workflow skills, and a complete coordination system mirroring real studio hierarchy.

#ai-agents#multi-agent#template#workflow-automation+6
7.8k1.2k5
Shell

bmalph

LarsCowe

A Safe

Unified AI Development Framework - BMAD phases with Ralph execution loop

#cli-tool#ai-agents#workflow-automation#multi-agent+4
334334
TypeScript

always-on-memory-agent

agents

A Safe

Sample code and notebooks for Generative AI on Google Cloud, with Gemini on Vertex AI

#ai-agents#llm#memory#framework+6
16.5k4.1k5
Jupyter Notebook

free-code

paoloanzn

D Risk

The free build of Claude Code. All telemetry removed, security-prompt guardrails stripped, all experimental features enabled.

#cli-tool#llm#ai-agents#code-generation
3.4k1.2k3
TypeScript

ComfyUI-Qwen-TTS

flybirdxx

A Safe

A Simple Implementation of Qwen3-TTS's ComfyUI

#plugin#voice#ai-agents#llm+2
1.3k1353
Python

zeroleaks

ZeroLeaks

A Safe

AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities

#security#llm#ai-agents#multi-agent+5
539863
TypeScript

murmure

Kieirra

A Safe

Fully local, private and cross platform Speech-to-Text with LLM Post-processing

#voice#local-first#self-hosted#desktop-app+2
639623
TypeScript

claude-scientific-skills

K-Dense-AI

A Safe

A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

#ai-agents#research#library#data+4
17k1.9k2
Python

CoPaw

agentscope-ai

A Safe

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

#ai-agents#llm#multi-agent#memory+7
14.1k1.9k4
Python

sayna

SaynaAI

A Safe

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

#voice#ai-agents#real-time#streaming+6
165274
Rust

Scrapling

D4Vinci

A Safe

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

#web-scraping#framework#library#cli-tool+5
34.2k2.8k2
Python

marketing-dashboard

builderz-labs

A Safe

Open-source marketing operations control center for AI agent teams (CRM, outreach, content, analytics) powered by OpenClaw + SQLite.

#ai-agents#workflow-automation#data#analytics+6
185404
TypeScript

reader

jina-ai

A Safe

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

#web-scraping#llm#api#rag+3
10.4k7915
TypeScript

paperdebugger

PaperDebugger

A Safe

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

#ai-agents#multi-agent#mcp#browser-extension+5
1.4k685
TypeScript

claude-code-best-practice

shanraisshan

A Safe

practice made claude perfect

#ai-agents#llm#workflow-automation#context-engineering+6
30.3k2.6k5
HTML

gsd-2

gsd-build

A Safe

A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture

#ai-agents#code-generation#cli-tool#context-engineering
4k4095
TypeScript

xyops

pixlcore

A Safe

A complete workflow automation and server monitoring system.

#devops#server#workflow-automation#monitoring+1
3.7k3733
JavaScript

clawguard

JaydenBeard

A Safe

Activity monitor and security dashboard for Clawdbot - real-time analytics, risk analysis, and kill switch

#ai-agents#security#monitoring#plugin+1
135222
JavaScript

Decepticon

PurpleAILAB

B Good

Autonomous Hacking Agent for Red Team Testing

#ai-agents#security#framework#multi-agent+1
9491773
Python

guardian-cli

zakirkun

B Good

Guardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.

#ai-agents#security#cli-tool
1.3k2722
Python

ClawWork

HKUDS

A Safe

"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

#ai-agents#research#framework#multi-agent
7.8k1k2
Python

agentfield

Agent-Field

A Safe

Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.

#ai-agents#framework#mcp#memory+3
1.3k1945
Go

CodexSkillManager

Dimillian

A Safe

macOS app to manage your Codex skills

#ai-agents#desktop-app#context-engineering#plugin
978582
Swift

MemoryOS

BAI-LAB

A Safe

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

#ai-agents#memory#rag#mcp+2
1.3k1283
Python

mission-control

builderz-labs

A Safe

Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.

#ai-agents#multi-agent#mcp#workflow-automation+2
3.7k6325
TypeScript

ServerKit

jhd3197

A Safe

ServerKit is a lightweight, modern server control panel for managing web applications, databases, and services on your VPS or dedicated server. Built with Python/Flask backend and React frontend.

#devops#server#monitoring#self-hosted+1
284463
JavaScript

cognee

topoteretes

A Safe

Knowledge Engine for AI Agent Memory in 6 lines of code

#ai-agents#memory#knowledge-graph#rag+2
14.8k1.5k5
Python

opendataloader-pdf

opendataloader-project

A Safe

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

#data#rag#library#ocr
10.9k8225
Java

Skills-ContextManager

One-Man-Company

A Safe

A self-hosted web application for managing AI skills, workflows, and contexts with full MCP (Model Context Protocol) integration. Organize, manage, and dynamically load specialized knowledge bases into any AI Agent just by toggling your Skills On/Off in simple local hosted WEB UI.

#ai-agents#mcp#context-engineering#workflow-automation+1
65152
Python

get-shit-done

gsd-build

A Safe

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

#ai-agents#code-generation#cli-tool#context-engineering+1
46.4k3.8k31
JavaScript

claude-octopus

nyldn

A Safe

Put up to 8 AI models on every coding task — blind spots surface before you ship. Claude Code plugin.

#ai-agents#multi-agent#mcp#workflow-automation+1
2.2k1805
Shell

livekit

livekit

A Safe

End-to-end realtime stack for connecting humans and AI

#real-time#server#voice#self-hosted+1
17.9k1.8k3
Go

claude-mem

thedotmack

B Good

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

#ai-agents#memory#rag#mcp+2
44.3k3.3k3
TypeScript

stenoai

ruzin

A Safe

Privacy focused AI powered meeting intelligence using locally hosted Small Language Models. StenoAI Scribe for structured clinical notes in development.

#voice#desktop-app#local-first#llm
568823
HTML

voicebox

jamiepine

A Safe

The open-source voice synthesis studio

#voice#desktop-app#local-first
14.4k1.7k3
TypeScript

ruvector

ruvnet

A Safe

RuVector is a High Performance, Real-Time, Self-Learning, Vector GNN, Memory DB built in Rust.

#vector-database#rag#server#self-hosted
3.7k4483
Rust

strix

usestrix

A Safe

Open-source AI hackers to find and fix your app’s vulnerabilities.

#ai-agents#security#cli-tool#multi-agent
23k2.5k2
Python

pentagi

vxcontrol

A Safe

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

#ai-agents#security#framework#multi-agent+3
14k1.8k2
Go

openfang

RightNow-AI

A Safe

Open-source Agent Operating System

#ai-agents#framework#mcp#workflow-automation+2
16.1k2k3
Rust

autoresearch

karpathy

A Safe

AI agents running research on single-GPU nanochat training automatically

#ai-agents#research#llm#code-generation
63.3k8.9k3
Python

PraisonAI

MervinPraison

A Safe

PraisonAI 🦞 - Your 24/7 AI employee team. Automate and solve complex challenges with low-code multi-agent AI that plans, researches, codes, and delivers to Telegram, Discord, and WhatsApp. Handoffs, guardrails, memory, RAG, 100+ LLMs.

#ai-agents#framework#multi-agent#rag+2
6.2k8895
Python