Highlights
- Pro
Stars
Use Codex from Claude Code to review code or delegate tasks.
Harbor is a framework for running agent evaluations and creating and using RL environments.
Lightweight coding agent that runs in your terminal
A Tool to Visualize Claude Code's LLM Interactions
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
[KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations
Reinforcement Learning via Self-Distillation (SDPO)
NexRL is an ultra-loosely-coupled LLM post-training framework.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
A construction kit for reinforcement learning environment management.
This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners.
Benchmarking Semantic Query Processing Engines
verl: Volcano Engine Reinforcement Learning for LLMs
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
Official implementation of Selective Entropy Regularization (SIREN), proposed by paper 'Rethinking Entropy Regularization in Large Reasoning Models'.
AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
🏅 Collection of Kaggle Solutions and Ideas 🏅
A high-throughput and memory-efficient inference and serving engine for LLMs
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Nemotron-CORTEXA is an open-source software engineering agent that fixes GitHub issues.
LlamaIndex is the leading document agent and OCR platform
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN