Stars
The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.
An agentic skills framework & software development methodology that works.
aider is AI pair programming in your terminal
Train the smallest LM you can that fits in 16MB. Best model wins!
[ICLR 2026] When Does Divide and Conquer Work for Long Context LLM? A Noise Decomposition Framework
Codabench is a flexible, easy-to-use and reproducible benchmarking platform. Check our paper: https://hubs.li/Q01fwRWB0
🧠 两小时从 0 训出你的 64M 大模型。Train your own 64M LLM from scratch in 2 hours.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Lightweight coding agent that runs in your terminal
The official Python library for the OpenAI API
A lightweight, powerful framework for multi-agent workflows
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
🙌 OpenHands: AI-Driven Development
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
SGLang is a high-performance serving framework for large language models and multimodal models.
A high-throughput and memory-efficient inference and serving engine for LLMs
Development repository for the Triton language and compiler
Unofficial RSS feed generator for GitHub Trending
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x