AI 开源项目榜。

The open document intelligence platform for builders and hackers - DMS for the agentic world

这是一个基于Claude Skill的**AI人像Prompt生成系统**，能够从特征库中智能组合生成高质量的人像描述Prompt，并具备自动学习和库扩展能力。 核心能力: Prompt生成、特征提取、自动学习、智能审核、版本控制

Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

ACE (Autonomous Cognitive Entities) - 100% local and open source autonomous agents

open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a false sense of control.

Machine learning powered Karaoke app (with scores!)

OpenMMLab Foundational Library for Training Deep Learning Models

FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc.

CLI is all you need. The agent CLI harness.

Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

Simulation verification and physical deployment of robot reinforcement learning algorithms, suitable for quadruped robots, wheeled robots, and humanoid robots. "sar" represents "simulation and real"

Fast and customizable framework for automatic ML model creation (AutoML)

Tools for building GPU clusters

Fast, context-efficient repository tools for AI agents (MCP)

IBM Fully Homomorphic Encryption Toolkit For Linux. This toolkit is a Linux based Docker container that demonstrates computing on encrypted data without decrypting it! The toolkit ships with two demos including a fully encrypted Machine Learning inference with a Neural Network and a Privacy-Preserving key-value search.

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Obsidian + Claude Code: Rebuild Your Second Brain with AI · 橙皮书系列 · 用AI重建你的第二大脑

An AGENTS.md file for Swift and SwiftUI projects.

Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sharing.

Code and Data for Tau-Bench

Open-source observability tool that uses AI agents to self-heal your software

ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent

Comprehensive guide to learn RAG from basics to advanced.

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

Automated CAPTCHA solver usage examples.

A group of notebooks and other files which can help you learn AI from scratch.