AI OPEN SOURCE INDEX

AI 开源项目

收录近期活跃、Star 超过 100 的 AI 项目,覆盖 MCP、Skill、Agent、RAG 与模型生态。

1000 收录项目 28 开发语言 11 项目分类

PROJECT DIRECTORY

全部项目

找到 1000 个项目
Muesli-HQ

muesli

Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)

音频 / 语音apple-silicondictation
Swift 950 109

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

SkillAgent模型 / 推理agentagent-skills
Python 945 34
jjang-ai

mlxstudio

MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)

Agent模型 / 推理视觉 / 图像aiai-agents
Unknown 943 65

Uncensored local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text

模型 / 推理视觉 / 图像音频 / 语音image-generationspeech-to-text
JavaScript 939 263
heymrun

heym

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

MCPAgentRAGai-agentsai-agents-framework
Python 939 83

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

视觉 / 图像auto-regressive-diffusion-modelautoregressive-models
Python 921 52
NVIDIA-NeMo

labs-molt

暂无项目简介。

模型 / 推理
Python 913 87
sipyourdrink-ltd

bernstein

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline. Cluster mode, air-gap deploy. Status: beta. https://bernstein.run

Agent模型 / 推理AI 编程agent-fleetagent-infrastructure
Python 906 118
Tencent-Hunyuan

UniRL

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

模型 / 推理视觉 / 图像ai-infrastructurereinforcement-learning
Python 903 61

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

AgentRAG模型 / 推理agent-memoryai-agents
Jupyter Notebook 881 115
tophant-ai

aibeat

Break your AI before they do. Join Discord: https://discord.gg/8A6mFckxZ

Agent评测 / 安全agentsai-security
MDX 880 8
RongleCat

grok-app

Desktop workbench for Grok Build CLI — sessions, projects, media, automations (Tauri 2 · unofficial)

工作流 / 自动化
TypeScript 870 97
repoprompt

repoprompt-ce

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

MCPAgentAI 编程ai-agentscoding-agents
Swift 866 116

AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

模型 / 推理音频 / 语音aiaudiobook
Python 864 101
agentforce314

clawcodex

Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python. Up to 200X Cost Saving!

SkillAgent模型 / 推理agentai
TypeScript 863 154

Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.

MCPAgent模型 / 推理ai-agentautomation
JavaScript 845 120
zhitongblog

solomd

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

MCP模型 / 推理aiandroid
TypeScript 844 47
local-inference-lab

rtx6kpro

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

模型 / 推理
Python 841 57
emiliaprotocol

emilia-protocol

Consequence firewall for machine actions. EMILIA Gate verifies exact authority before money, code, permissions, infrastructure, or regulated state changes; the open protocol makes the evidence independently verifiable.

MCPAgent评测 / 安全agent-securityagentic-ai
TypeScript 841 13
unohee

OpenSwarm

OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.

SkillAgentRAGai-agentsai-coding
TypeScript 835 146
Raymondhou0917

speak-human-tw

「說人話」:繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡,順手校正中國用語與半形標點,給 Claude Code / Codex / Cursor 用。

SkillAgentagent-skillsai-writing
Python 832 92
benchflow-ai

awesome-evals

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

Agent模型 / 推理评测 / 安全agent-evaluationai-agents
Unknown 829 86
sgl-project

sglang-omni

SGLang-Omni empowers high-performance serving for TTS, ASR, speech and omni models.

模型 / 推理视觉 / 图像音频 / 语音asraudio-generation
Python 825 341
tong-io

tongflow

TongFlow : An Open-Source Multi-Modal GenAI Workflow Studio

视觉 / 图像音频 / 语音工作流 / 自动化3dai
TypeScript 820 118