Stars
DeepSeek-native agent framework: Cache-First Loop, R1 Thought Harvesting, Tool-Call Repair. TypeScript + Ink TUI.
Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.
Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.
React component library on Radix Primitives. Install packages on demand; use with theme or headless.
Your private AI assistant on your phone: simple, safe, and ready anytime. 你手机里的私人 AI 助手：简单、安全，随时可用。
🐙 Give your AI a life — open-source agent infrastructure for team collaboration.
Replace coding puzzles with real-work simulations.
HoneClaw (Hone-Financial) is dedicated to being a professional investment assistant that truly understands you.
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
Your personal AI research assistant that automatically reads, summarizes, organizes, and acts on academic papers.
[CVPR 2026] WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
🌱 SeedWorld — Plant a world. Watch it grow. An emergent world simulation engine powered by LLM. 给LLM一个世界设定,看它自己长出文明
In the AI era, why can't everyone be a Principal Investigator?
🐹 An Intelligent Phone That Never Sleeps.
HiMarket is an enterprise-level "AI Capability Marketplace and Developer Ecosystem Hub." It is not merely a simple aggregation of traditional APIs, but rather a comprehensive platform that packages…
Configurable Multi-layered AI Agentic Safety Framework
The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
Mobile-Agent: The Powerful GUI Agent Family
LLM-powered Agent Runtime with Dynamic DAG Planning & Concurrent Execution
Lilium AI: The ultimate personal AI agent framework for autonomous computer control. Featuring browser automation, shell execution, and multi-channel integration (WeChat/Telegram/Discord).
🏭 Mega Scale Multimodal DataPipeline for SOTA Foundation Models
[NeurIPS 2025 Spotlight] Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning
This project contains a simulation framework for leveraging deep reinforcement learning in studying of the fluid dynamics. Stable BaseLine 3 and WaterLily are essential.
An OpenClaw-native knowledge retention skill that turns raw inputs into structured practice so you can use what you know, not just store it.
UI-Venus is a native UI agent designed to perform precise GUI element grounding and effective navigation using only screenshots as input.
Build your own Cowork, AI Scientist and other SoTA Agents just by editing config files. Support anthropic skills. An infinite-horizon agent framework designed for long-running, complex tasks.