# makezur/agenticSTAR

> A harness for agentic shape tracking and reconstruction of articulated objects from monocular video: a coding agent (Codex or Claude Code) writes a Blender script that builds the object from primitives, poses it per frame and declares joints, then renders and iteratively compares to the frames. Output is a GLB with named parts and pose.json with per-frame poses.

- Magnitude: 0.7 out of 10 — Steady
- Stars: 199 total · +0 stars on 2026-09-27 (UTC), ≈ 1 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2026-09-10 · Last push: 2026-09-23
- GitHub: https://github.com/makezur/agenticSTAR · Homepage: https://agenticstar.github.io/ · Page: https://gitnova.dev/en/r/makezur/agenticSTAR

## Useful for

- Reconstruct a 3D model and per-frame poses of an articulated object from a recorded video
- Run the pipeline on your own clip: extract frames, masks and cameras via tools/make_capture.py
- Compare how different coding agents handle the reconstruction task by inspecting iterations under runs/

## Why it’s here

- The repository is 17 days old and already has 199 stars.
- Recent forks include notable developers: @mbrukman (387 followers).

## 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: 9
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 10 per day
- Usual pace: 8 per day

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

2026-10-04 … 2026-11-02: 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 12 days

09-16 3.7, 09-17 2.8, 09-18 1.6, 09-19 1.6, 09-20 2.3, 09-21 2.7, 09-22 2.1, 09-23 2.0, 09-24 2.0, 09-25 1.2, 09-26 1.2, 09-27 0.7

---

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.