DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Agentic STAR

AgentSTAR is a harness where a coding agent (Codex or Claude Code) reads a monocular video, builds an articulated object in Blender, poses it per frame, and iterates until the renders match the frames.

Trended earlier

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

3 use cases

  • Reconstruct the garden shears example end to end

    Run one supervised agent session on the committed example and get a GLB and pose.json.

    View prompt
    In the agenticSTAR repo, set up the environment with ./install.sh and run the garden shears example with Claude Code using tools/run_kf.sh on examples/garden_shears/capture:0 on GPU 0. Expect runs/ to contain scene.py, mesh/object.glb and mesh/pose.json. Verify that mesh/pose.json holds per-frame poses and joint states before reporting success.
  • Turn your own video of an object into a 3D capture

    Extract frames, add object masks, run Pi3X cameras, then let the agent rebuild the object.

    View prompt
    Using the agenticSTAR repo, convert <video-file> into a capture with tools/video_to_frames.sh and tools/make_capture.py, then run tools/run_kf.sh with --agent claude on the resulting capture. Expect mesh/object.glb and mesh/pose.json under runs/. Verify that the mask folder has one PNG per extracted frame before starting the run.
  • Compare Codex and Claude Code on the same capture

    Run the same capture with both supported agents and compare the resulting poses.

    View prompt
    In the agenticSTAR repo, run tools/run_kf.sh on examples/garden_shears/capture:0 once with --agent codex and once with --agent claude. Expect two runs/ directories, each with mesh/pose.json. Verify that both runs finished or hit their timeout before comparing outputs.

How to use Agentic STAR

  1. Check you have what it needs: Linux x86_64 host with an NVIDIA GPU; micromamba, git, curl, tar, xz, python3, tmux, bubblewrap, iproute2 and ffmpeg installed on the host; Root or CAP_NET_ADMIN for the sandbox network namespace.
  2. Open makezur/agenticSTAR on GitHub and read the README and license.
  3. Run ./install.sh to build the artscript env, Blender 4.2.5 and the pi3x env.
  4. Run export ANTHROPIC_API_KEY=sk-ant-... in the shell you will use.
  5. Run tools/install_claude_bwrap.sh once so the key is stored in a state dir outside the checkout.
  6. Run tools/run_kf.sh --agent claude --timeout-hours 4 examples/garden_shears/capture:0.

These steps come from our top use case, Reconstruct the garden shears example end to end, which also has a copy-paste agent prompt.

Agentic STAR alternatives · Best AI repos for Research

About this repo

Requirements

  • Linux x86_64 host with an NVIDIA GPU
  • micromamba, git, curl, tar, xz, python3, tmux, bubblewrap, iproute2 and ffmpeg installed on the host
  • Root or CAP_NET_ADMIN for the sandbox network namespace
  • An Anthropic API key for Claude Code or an OpenAI API key for Codex
  • claude and/or codex available on PATH
Maintain Agentic STAR? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/makezur-agenticstar.svg)](https://dedupedai.com/use-cases/makezur-agenticstar/?ref=badge)

More badge styles and HTML

Questions about Agentic STAR

What is Agentic STAR?

AgentSTAR is a harness where a coding agent (Codex or Claude Code) reads a monocular video, builds an articulated object in Blender, poses it per frame, and iterates until the renders match the frames. It is an open-source project on GitHub: https://github.com/makezur/agenticSTAR.

Who is Agentic STAR for?

Computer vision and robotics researchers, and engineers who need joint-level 3D models of articulated objects from ordinary video.

What can I do with Agentic STAR?

3 use cases so far, for example: Reconstruct the garden shears example end to end; Turn your own video of an object into a 3D capture; Compare Codex and Claude Code on the same capture. Each has steps and a copy-paste agent prompt.

What do I need to run Agentic STAR?

Linux x86_64 host with an NVIDIA GPU; micromamba, git, curl, tar, xz, python3, tmux, bubblewrap, iproute2 and ffmpeg installed on the host; Root or CAP_NET_ADMIN for the sandbox network namespace; An Anthropic API key for Claude Code or an OpenAI API key for Codex.

What are alternatives to Agentic STAR?

Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, Evo Bot, AI Engineering Course.

Is Agentic STAR safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.