AI 开源项目榜。

纯手工绘制 Transformer 架构图；Drawing the Transformer architecture diagram by hand

MCP server for TouchDesigner

专业影视导演 Agent，基于剧本完成导演定调→节奏规划→剧本微调→分镜拆解，最终输出标准九列分镜表（xlsx）； 深度融合世界顶级导演视听理论，内置数十种影片类型导演风格模板库，支持类型交叉组合； 覆盖概念超短片/短片/长片全格式，将文字剧本转化为可落地的专业拍摄方案。

The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, and multi-image queries for generating captions or responses.

Voice & Video Calling and Text Chat App for Flutter

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100% offline using MLX.

An on-device LLM understands your entire life, then proactively offers to get your work done through computer use.

A hybrid Windows endpoint security platform powered by machine learning, YARA rules, cloud analysis, and kernel-level behavioral protection.

HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

AI-powered assistant workbench for FreeCAD — generate 3D models from natural language

⚡ DocsAgent — give your AI agents instant, private access to your personal knowledge base (Zotero, Obsidian, Apple Notes supported now, local docs on the road). Native C++ search core: BM25 + passage ranking in ~15 ms. MCP server for Claude, Cursor, Cline & any MCP client.

A list of the most popular AI Topic repositories on GitHub based on the number of stars they have received.| AI相关主题Github仓库排名，每日自动更新。

SDK for Frontier Embedded Agents.

A Tree Search Library with Flexible API for LLM Inference-Time Scaling

Customer-run client for Secure MCP Tunnel: connect private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit without exposing them to the public internet.

An open, curated collection of Agent Skills for scientific research — clone it, use it, extend it!

Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build animations, and an independent critic review before delivery.

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

Know how much Claude Code, Codex, Cursor, Copilot and 70+ other AI coding tools you have left — a free, open-source macOS monitor on the edge of your screen.

Long Horizon Terminal Benchmark with Dense Reward Grading

Generalist and Lightweight Model for Text Classification

KISS Sorcar: Keep it Simple, Stupid AI General Purpose Agent Framework for Long Horizon Tasks and AI Discovery

Curated list of 150+ tools, skills, subagents & plugins for OpenAI Codex CLI

Orchard-Agentic is a collection of open-source work on agentic modeling

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

Identify and simulate extended friction models for servo-actuators

An entire marketing department as one Claude skill. 14 modules: audits scored 0-100, an 18-tactic hook engine, copy graded before you see it, ad diagnosis, GEO, email, launches, pricing. Works in Claude, Codex and Cursor.

The open .char format for consistent characters. Face, body, wardrobe & voice in one file, consistent across every model.

LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.