slime is an LLM post-training framework for RL Scaling.

The multi-agent toolkit: framework, runtime, and control plane.

Build resilient language agents as graphs.

Vibe Workflow Platform for Non-technical Creators.

The integration of HugeGraph with AI/LLM & GraphRAG

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios

A course on aligning smol models.

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.

Fast and memory-efficient exact attention

An open protocol enabling communication and interoperability between opaque agentic applications.

🌐 WebAgent for Information Seeking built by Tongyi Lab: WebWalker & WebDancer & WebSailor https://arxiv.org/pdf/2507.02592

On the basis of integrating VMInd into OpenManus for data analysis, processing, and visualization generation, enhance the ability to annotate and annotate specific scenarios

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Fully local web research and report writing assistant