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
1,456 results
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
⚡ TabPFN: Foundation Model for Tabular Data ⚡
A framework for few-shot evaluation of language models.
Reconstruct and validate C/C++ code from compiled programs with AI.
《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
Run a 105 GB AI model on a 48 GB Mac. Qwen3.8-Flash-Next (125B mixture of experts) streams its experts from SSD through a slot cache. Native Swift on MLX and Metal: one binary, no Python, Ollama- and OpenAI-compatible APIs.
A Flutter LLM Chat Client. Support Mobile & Desktop.
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
SOTA Open Source TTS
The agent that remembers and learns.
Autonomous Hacking Agent for Red Team
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
Vibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent：每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐，由你自己的 Agent 驱动投资研究。基于开源的 Codex Harness 打造。
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
Learn LLM internals step by step - from tokenization to attention to inference optimization.
open-source agentic AI data assistant for the next generation of AI + Data products.
Local, open-source AI app builder for power users ✨ v0 / Lovable / Replit / Bolt alternative 🌟 Star if you like it!
The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Automated Penetration Testing Agentic Framework Powered by Large Language Models
24,540 repositories in the index in total.
