Répertoire open source

adapter-hub

adapters

★ 2 829

A Unified Library for Parameter-Efficient and Modular Transfer Learning

alsk1992

CloddsBot

★ 2 826

Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains. Scans for edge, executes instantly, manages risk while you sleep. Agent commerce protocol for machine-to-machine payments. Self-hosted. Built on Claude.

jherrodthomas

automotive-skills-suite

★ 2 825

100+ installable Claude skills covering Engineering areas such as, ISO 26262 functional safety, ISO/SAE 21434 cybersecurity, ISO 21448 SOTIF, AIAG-VDA quality (APQP/PPAP/FMEA), Automotive SPICE, and continuous improvement tools — every builder paired with a confirmation reviewer.

leptonai

leptonai

★ 2 824

A Pythonic framework to simplify AI service building

tach-org

tach

★ 2 824

A Python tool to visualize + enforce dependencies, using modular architecture 🌎 Open source 🐍 Installable via pip 🔧 Able to be adopted incrementally - ⚡ Implemented with no runtime impact ♾️ Interoperable with your existing systems 🦀 Written in rust

yaojingang

yao-open-prompts

★ 2 822

Practical bilingual AI prompt library for prompt engineering, work, learning, content, marketing, and everyday use.

sahibzada-allahyar

YC-Killer

★ 2 821

A library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups.

zinja-coder

jadx-ai-mcp

★ 2 820

Plugin for JADX to integrate MCP server

datachain-ai

datachain

★ 2 820

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Vexa-ai

vexa

★ 2 819

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

OpenDCAI

DataFlex

★ 2 818

Data-centric LLM training with dynamic sample selection, domain mixture optimization, and example reweighting inside the LLaMA-Factory training loop.

huggingface

setfit

★ 2 817

Efficient few-shot learning with Sentence Transformers

EvanBacon

serve-sim

★ 2 816

The `npx serve` of Apple Simulators.

rebelytics

one-skill-to-rule-them-all

★ 2 816

The meta-skill that builds and improves all your skills, including itself. Watches your work sessions (autonomous or human-led), captures patterns, corrections and judgement calls, and turns them into skill improvements and new skill candidates for your review. Practical application of the Augmented Expertise methodology. Open source: CC BY 4.0.

zhizhuodemao

js-reverse-mcp

★ 2 815

AI Agent-first JS 逆向 MCP Server：有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测，可选 CloakBrowser。

teaql

teaql-agent-kit

★ 2 813

Exécution déterministe pour l'IA non déterministe. Il fournit des tâches, des invites, des guides et des rapports pour observer le comportement des agents de codage lorsqu'ils travaillent avec des logiciels d'entreprise basés sur TEAQL.

gamosoft

NoteDiscovery

★ 2 813

Your Self-Hosted Knowledge Base

ClassIsland

ClassIsland

★ 2 812

. Un outil d'affichage d'informations d'horaires puissant, personnalisable et multiplateforme, adapté aux écrans multimédia de classe, qui peut afficher diverses informations en un coup d'œil.

philipperemy

keras-attention

★ 2 808

Keras Attention Layer (Luong and Bahdanau scores).

mll-lab-nu

RAGEN

★ 2 807

Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics