Stars
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.
SGLang is a high-performance serving framework for large language models and multimodal models.
verl: Volcano Engine Reinforcement Learning for LLMs
An open-source AI agent that lives in your terminal.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
A high-throughput and memory-efficient inference and serving engine for LLMs
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / U…
Our library for RL environments + evals
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A metasearch library that aggregates results from diverse web search services
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
slime is an LLM post-training framework for RL Scaling.
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
A compilation of the best multi-agent papers