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
1,442 results
📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。
Universal LLM Deployment Engine with ML Compilation
🔍 Google SEO's full docs as an AI prompt machine — drop it into your AI assistant to map every public route, audit each page against Google's rules, and fix the gaps step by step.
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.
Run local LLMs like Gemma, Qwen, and LLaMA on Android for offline, private, real-time chat and question answering with LiteRT and ONNX Runtime.
Earth system foundation model data, training, and eval
Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
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
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
Build a modern LLM from scratch. Every line commented. Explained like we are five.
TabFM (Tabular Foundation Model) is a pretrained tabular foundation model developed by Google Research for tabular data regression and classification.
Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
Machine learning compiler based on MLIR for Sophgo TPU.
eLLM: Run Long-Horizon Inference Faster on CPUs Than on GPUs
Translate a whole season of subtitles in one pass — .srt/.ass/.vtt/.lrc, 120+ languages, 27 LLM providers, timing untouched ｜ 整季字幕一次译完，时轴不动，支持 120+ 语言
Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.
LLM KV cache compression made easy
「可能是全网最全的」📘 面向小白的 AI 编程 CLI 中文教程：Claude Code + Codex 92 篇精修
Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context
Reconstruct and validate C/C++ code from compiled programs with AI.
No description
24,545 repositories in the index in total.
