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
1,455 results
The best way to get AI coding agents to solve hard problems in complex codebases.
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
State is a machine learning model that predicts cellular perturbation response across diverse contexts
Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等
AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models
Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.
A Powerful web scraper powered by LLM | OpenAI, Gemini & Ollama
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。
Earth system foundation model data, training, and eval
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
LLMs and VLMs with MLX Swift
Cell type annotation for single-cell RNA-seq using multi-LLM consensus
Python SDK for ACP clients and agents.
Tools for merging pretrained large language models.
Gemma open-weight LLM library, from Google DeepMind
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.
Collection of leaked system prompts
22 prompt engineering techniques with hands-on Jupyter Notebook tutorials, from fundamental concepts to advanced strategies for leveraging LLMs.
Turn any webpage into structured data using LLMs
24,540 repositories in the index in total.
