# physicalvision/artisan

> Artisan is a multi-agent research pipeline that generates physically grounded articulated 3D assets from a text description and optional reference images, and ships with a benchmark for evaluating them.

- Magnitude: 1.2 out of 10 — Steady
- Stars: 91 total · +0 stars measured 2026-10-15, 00:21–02:36 UTC, ≈ 6 by evening
- Star trust: star growth looks organic
- Category: Science & research · Language: Python · License: Apache-2.0 · Created: 2026-10-09 · Last push: 2026-10-12
- GitHub: https://github.com/physicalvision/artisan · Homepage: https://physicalvision.github.io/artisan/ · Page: https://gitnova.dev/en/r/physicalvision/artisan

## Useful for

- Generate an articulated 3D asset from text and an image via ./run.sh run
- Evaluate assets on appearance, geometry, material and collision metrics
- Open the interactive viewer and move joints of generated assets

## Why it’s here

- Star-counter measurements on 2026-10-15 (UTC), 00:21–02:36: 91 → 91 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +6 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 91 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #190.

## 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: 2
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 14 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-09 … 2026-10-15: 0, 0, 35, 36, 12, 8, 0

## Spotted in now

- Top new repositories this week: #190

## Similar by description

1. **4DCodeBench/4DCodeBench** — 0.7 · Steady · AI agents · Python · +0 stars measured 2026-10-15, 00:30–02:39 UTC, ≈ 2 by evening
   A benchmark for evaluating coding agents on inverse graphics: the agent watches a video of a physical event and writes graphics code that reconstructs the scene's geometry, motion, and appearance. 200 videos: 100 real and 100 synthetic.
   Full card: https://gitnova.dev/en/r/4DCodeBench/4DCodeBench.md

---

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 2026-10-15 02:41 UTC, updated every 30 minutes.