makezur/agenticSTAR
AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
About the project
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.
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/
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 3 stars so far today, about 4 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 8 days old and already has 90 stars.
- Recent forks include notable developers: @mbrukman (387 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 90
- Stars in a day
- 4
- Forks
- 5
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- MIT
- Created
- September 10, 2026
- Last push
- September 10, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 16, 2026Top new repositories this week: #152
Similar projects
-
8.8
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.
-
8.5
tamaratran/fast-jev-compaction
Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…
-
7.9
hypit-ai/hypit
Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.
-
7.9
Tencent/BrowserSkill
BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.
-
7.0
korcarc/text-humanizer
A Python tool that rewrites AI-generated text through an LLM and translation pipeline to bypass detectors like Turnitin and GPTZero. Supports 8 languages and requires a DeepSeek API key.
-
6.8
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.