Starred repositories
An agentic skills framework & software development methodology that works.
An LLM post-training framework with vLLM for RL Scaling
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
Toolkit for Seamlessly Enabling RL Training on Any Agent with Bedrock AgentCore.
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
The absolute trainer to light up AI agents.
Agentic RL on Any Harness at Scale
A fast, minimal ES2023 JavaScript runtime built in Rust.
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
The financial transactions database designed for mission critical safety and performance.
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
LLM Inference via Triton (Flexible & Modular): Focused on Kernel Optimization using CUBIN binaries, Starting from gpt-oss Model
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
A project implementing various agentic RL based on the Slime post-training framework
CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.
The agent that grows with you
Make Any Website into CLI & Use your logged-in browser by AI agent.
Lightweight coding agent that runs in your terminal
A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.