Stars
SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and …
🔮 Run all your AI coding agents in tmux: jump to the one that needs you, spawn them into worktrees, and hand work between them
An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks
[CoRL 2026] Official data processing repository for "GazeVLA: Learning Human Intention for Robotic Manipulation"
[RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
A simulation benchmarking platform for evaluating generalist robot policies
AgentGarten: Code Worlds for Evolving Agents
Solo four-month reimplementation of Sunday Robotics' Skill Capture Glove. End-to-end: PCB, firmware, capture pipeline, HLoc-based pose tracking, and an ACT policy on 182 manipulation demos.
GPT-6 Astra for embodied AI and robotics.
A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
Modular and Automated Scene Generation for Policy Learning and Evaluation
A curated research map of coding agents for robot learning
gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots
Skill and tool bundles for gap (graph as policy) — Anthropic Agent Skills format, discovered by path
World Action Model, VLA failure detection/correction, Efficient VLA
A curated list for Self-Improvement in Foundation Model Based Agentic Systems.
FoundationPoseROS2 is a ROS2-integrated system for 6D object pose estimation and tracking, based on the FoundationPose architecture. It uses RealSense2 with the Segment Anything Model 2 (SAM2) fram…
Fetching Embodied AI Paper from ArXiv automatically
[CoRL 2026] Official code repository for "GazeVLA: Learning Human Intention for Robotic Manipulation"