No VLA needed: gpt6 astra self-calibrates an SO-101 arm and sorts LEGOs in MuJoCo
mishig25 · x · 2026-09-15
Hugging Face's mishig25 released a reproducible SO-101 arm demo: instead of a VLA model, gpt6 astra self-calibrates the front camera and picks up three LEGO-like blocks into a box, all in MuJoCo simulation—no physical robot needed.
Resources are open on a Hugging Face bucket (README, scripts, verification):
- Ships a copy-paste prompt for your coding agent: read README, download files, use uv for env management, run calibration and the sorting demo, verify all three blocks land in the box;
- The controller sends six joint-position targets with physical gripper contacts; includes REPRODUCIBILITY. and a verification manifest.
Related event: gpt6 Controls SO-101 Robot Arm to Sort LEGO in MuJoCo(2 posts)→
More from coding & agent
- FlyWire publishes DIY guide to simulate a fly brain with ~160k neurons — patrickmineault · 2026-09-15
- 'Relay': a lightweight Codex skill for thread-driven multi-agent orchestration — daniel_mac8 · 2026-09-15
- Relay: open-source Codex skill hands bounded jobs to fresh tasks with one-message callbacks — daniel_mac8 · 2026-09-15
- Bolt Forge launches free until Oct 14 with GLM, DeepSeek and Kimi plus up to 50x more usage — HeyAmit_ · 2026-09-15
- A Practical Guide to Building an Agent Harness From Scratch — omarsar0 · 2026-09-15
- How to build an agent harness from scratch: LLM module, tools module, and the ReAct route — ryunuck · 2026-09-15