Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant

URDF-Studio is a web-based visual URDF robot modeler with 3D workspace, structured skeleton/detail/hardware workflows, motor library integration, MuJoCo export, and AI assistance.

Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉

Pre-build reality check for AI coding agents. Scans GitHub, HN, npm, PyPI, Product Hunt. MCP server. 290+ stars.

Repo of "LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving""

Unified Codebase for Advanced World Models.

Depth Anything 3

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

SAM 3D Objects with Multi-view Images

A Paper List for Humanoid Robot Learning.

🦞 Just talk to your agent — it learns and EVOLVES 🧬.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Official Repo for TiPToP: A Modular Open-Vocabulary Planning System for Robotic Manipulation

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Claude Code skill for orchestrating multiple agents and complex workflows

[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control

An open-source SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skills and subagents, it handles different levels of tasks that could take minute…

The open source coding agent.

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Official implementation of "HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control"

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code