From-scratch multi-GPU LLM inference engine: paged KV cache, continuous batching, prefix caching, tensor parallelism, OpenAI-compatible server. Custom Triton kernels, vLLM-class throughput.

Browser Agent

A high-throughput and memory-efficient inference and serving engine for LLMs

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!

No fortress, purely open ground. OpenManus is Coming.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

An open-source RAG-based tool for chatting with your documents.