A web-based collaborative LaTeX editor (CE extended with free premium features)

Overleaf CLI - pull, push, sync, compile LaTeX projects from your terminal. Git remote helper, MCP server for AI agents, and TypeScript library.

High-Performance Serving Runtime for Robotics Models

An open-source, hand-worn variant of UMI for collecting bimanual manipulation data without a robot in the loop: modular for any parallel-jaw gripper.

The Dream Gripper is an open-source, 3d-printable gripper for the TRLC-DK1 that can pick up and reliably hold anything from a o ringt's scope was to pick up anything from an o-ring to an actuator.

GPT-6 Astra for embodied AI and robotics.

Addressing the Orchestration Gap in Generalist Robots via Physical Agency

WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models

MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos

[IROS 26 ScaleInfra Workshop Best Tool Paper] Involving over 50 Advanced Manipulation Policies

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".

[RSS 2026] Causal video-action world model for generalist robot control

Comet: agent skill harness for turning ideas into evaluated workflows

What Enables In-Context Behavior Prompting for Manipulation?

Advancing Open-source World Models

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

Official Repository for MolmoAct2

An end-to-end open ecosystem for robot learning

A Minimalist, Batteries-included Repository for Advancing World Model Science.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io

DEXTRAH

Code release for paper "Test-Time Training Done Right"

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.