RAX harness: coding agents that learn robot tasks by online exploration
☆320Oct 24, 2026Updated 2 weeks ago
Alternatives and similar repositories for rax
Users that are interested in rax are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Task skills robot agents learned on real robots, one library per embodiment☆19Oct 19, 2026Updated 2 weeks ago
- ASPIRE: Agentic /Skills Discovery for Robotics☆965Oct 16, 2026Updated 3 weeks ago
- A Unified Robot-Use Agent Harness Across Environments☆289Updated this week
- [CoRL 2026] Code for "FACT: Failure-Aware Causal Training for World‑Action Models"☆109Sep 15, 2026Updated last month
- The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and ver…☆240Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Official code for the SEAR benchmark☆39Oct 22, 2026Updated 2 weeks ago
- Robot-agent harness with a CLI and local Web console for LIBERO short evaluation☆175Oct 20, 2026Updated 2 weeks ago
- The offcial repo of "Towards Agentic Robots: Model, Data, Environment, and Harness"☆165Updated this week
- ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop ph…☆344Sep 9, 2026Updated last month
- Official implementation of Video Prediction Policy 2: Predict Better, Act Better☆366Oct 19, 2026Updated 3 weeks ago
- Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens☆215Updated this week
- GPT as Policy☆664Sep 16, 2026Updated last month
- Official Implementation of Flexible Locomotion Learning with Diffusion Model Predictive Control☆35Apr 18, 2026Updated 6 months ago
- RPent: Agentic Infrastructure for the Physical World☆1,723Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- GPT-6 Astra for embodied AI and robotics.☆1,239Oct 28, 2026Updated last week
- A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.☆533Updated this week
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,644Aug 20, 2026Updated 2 months ago
- Official repository of B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations.☆143Jul 22, 2026Updated 3 months ago
- GPT-Policy: In-Context Robot Learning with VLM Agents☆360Oct 17, 2026Updated 3 weeks ago
- ☆56Oct 12, 2026Updated 3 weeks ago
- What Enables In-Context Behavior Prompting for Manipulation?☆142Updated this week
- ☆98Oct 31, 2026Updated last week
- An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks☆408Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ICML 2026] A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation☆914May 28, 2026Updated 5 months ago
- Official Repository of Agentic World Action Models☆163Updated this week
- Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".☆1,178Updated this week
- The open-source model suite for robotics data engine by NVIDIA GEAR☆97Updated this week
- ☆47Sep 30, 2026Updated last month
- preview of PhysicalRSI infra an engine☆144Nov 1, 2026Updated last week
- In‑Context World‑Action Modeling from Human Videos for Open‑Ended Task Generalization☆452Sep 15, 2026Updated last month
- ☆13Dec 4, 2025Updated 11 months ago
- ☆19Nov 1, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Implementation of RoboTTT proposed by Yunfan Jiang et al. of Stanford and Nvidia☆113Sep 17, 2026Updated last month
- Agents for robot physical reasoning☆33Oct 7, 2026Updated last month
- X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining☆79Jun 18, 2026Updated 4 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,976Jul 9, 2026Updated 3 months ago
- Code for kai0, including training, inference and data collection.☆451Mar 9, 2026Updated 7 months ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,761Apr 19, 2026Updated 6 months ago
- Just a VLM Agent Can Play Robots☆613Updated this week