Stars
An open source vending machine benchmark: a long-horizon agentic business simulation served over MCP, shipped as a Harbor task.
[COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents
The agent that grows with you
DeepSeek Harness: Everything is a Plugin.
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
An interface library for RL post training with environments.
Turn any webpage into structured data using LLMs
Supercharge Your LLM Application Evaluations 🚀
An open source environment for digital agents.
[CVPR 2026] OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
GLM-SIMPLE-EVALS: The evaluation repository for the GLM-4.5 series of models by Z.ai.
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
A PyTorch native platform for training generative AI models
Claude Code dashboard with usage stats, error analysis, and sharable feature
Our library for RL environments + evals
250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
An open-source tool for LLM prompt optimization.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
State-of-the-art LLM compression, built for production inference with vLLM
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Cost-efficient and pluggable Infrastructure components for GenAI inference
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.