# air-embodied-brain/Zetta-Embodiment

> Zetta is a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. It targets robotics and VLA researchers working with LIBERO-Pro, RoboCasa, RoboTwin, and Genie Sim.

- Magnitude: 0.0 out of 10 — Steady
- Stars: 1,246 total · +0 stars on 2026-09-27 (UTC), ≈ 0 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · Created: 2026-08-18 · Last push: 2026-09-19
- GitHub: https://github.com/air-embodied-brain/Zetta-Embodiment · Page: https://gitnova.dev/en/r/air-embodied-brain/Zetta-Embodiment

## Useful for

- Run an evolution campaign on LIBERO-Pro or RoboCasa to improve recovery skills without retraining the policy
- Validate Critic-Recovery candidates via same-seed gate and held-out seeds before promotion
- Deploy a VLA runtime with Pi0.5 or GR00T for a specific simulator using install_vla_env.sh

## Why it’s here

- The repository is 40 days old and already has 1,246 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 83
- Issues and pull requests: 34
- Watchers: 31
- Average over the last week: 0 per day
- Usual pace: 29 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-14 2.3, 09-15 2.3, 09-16 2.2, 09-17 2.0, 09-18 1.7, 09-19 1.3, 09-20 0.4, 09-21 0.5, 09-22 0.0, 09-23 0.0, 09-24 0.0, 09-25 0.0, 09-26 0.0, 09-27 0.0

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-27 00:15 UTC, updated every 30 minutes.