AI 开源项目榜。
Train transformer language models with reinforcement learning.
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.
Multiplayer agent harness for work.
"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"
MiniCPM5: SOTA on-device LLMs, small yet powerful.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
Review-first terminal diff viewer for agentic coders
The backtesting engine that gives you an unfair advantage. Run thousands of trading ideas before others finish one.
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
A self-hosted email client with an AI agent, running entirely on Cloudflare Workers
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。
An end-to-end production workspace for AI-generated short dramas. From script input to structured storyboarding, consistency management, shot preparation, video generation, and export.
FlashInfer: Kernel Library for LLM Serving
ChatGPT官网接口纯协议的逆向实现，支持GPT-Image-2模型、文本模型，兼容OpenAI接口协议，在线批量生图/编辑图，号池管理，支持可编辑PPT/PSD文件逆向，支持导入CPA、sub2api号池 、支持接入Cherry Studio、New Api 等软件
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.
GPT Image 2/2.5 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
Achieve state of the art inference performance with modern accelerators on Kubernetes
A persistent workspace for development work that self-improves and continues beyond one session.
PDF 全文翻译，保留排版双语对照 · 2.4 亿文献检索一键入库 · 文库知识库问答 · AI 精读论文、综述与思维导图 · 列表直显期刊分区 / 中科院 / JCR / 影响因子 · 免插件网页版 app.ai4paper.pro · 适配 Zotero 7–10
A agent framework based on the tutorial hello-agents
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.
闲鱼智能客服系统，支持多账号管理、AI自动回复、自动发货确认、多渠道消息通知，提供完整的 Web 管理后台
一个基于 283 万字语料统计的去 AI 味 skill · An AI-tone removal skill grounded in a 2.83-million-character corpus study
Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness directly into your terminal.
说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts.