✨ Agentic chat experience in your terminal. Build applications using natural language.

Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

verl: Volcano Engine Reinforcement Learning for LLMs

The absolute trainer to light up AI agents.

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

MiroThinker is a series of open-source agentic models trained for deep research and complex tool use scenarios.

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

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖

AndroidWorld is an environment and benchmark for autonomous agents

RL research on Android devices.

《MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation》

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

Scaling Preference Data Curation via Human-AI Synergy

Tongyi Deep Research, the Leading Open-source Deep Research Agent

SkyRL: A Modular Full-stack RL Library for LLMs

ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World

My learning notes for ML SYS.

ZeroGUI: Automating Online GUI Learning at Zero Human Cost

Self-Adapting Language Models

Copy anything for llm

[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

Train your Agent model via our easy and efficient framework

⭐A lightweight open-source dart library for obtaining The Purple Star Astrology (Zi Wei Dou Shu) astrolabe information.. 支持多语言轻量级获取紫微斗数排盘信息的flutter开源库。