Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,475 results
一个基于LLM的演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型，提供丰富的模板和样式选择，让用户能够创建高质量的演示文稿。
Efficient Triton Kernels for LLM Training
TokenSpeed is a speed-of-light LLM inference engine.
微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex
A simple, performant, and scalable Jax LLM!
A framework for few-shot evaluation of language models.
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。
Native iOS and Android client for Open WebUI, plus direct OpenAI-compatible, Ollama, and OpenRouter connections and self-hosted Hermes agents.
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI
Web, Desktop & Mobile client for Codex, Claude Code, OpenCode, Kimi, Augment Code, Qwen, fully end-to-end encrypted
♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️
Native iPhone app for your Hermes agent
Custom AI agent platform to speed up your work.
HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
24,523 repositories in the index in total.
