Home Projects VoxPoser
VoxPoser
Python

VoxPoser

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

by huangwl18 · GitHub
Stars
Forks
Trending
License
Created
Last commit
Category
Language
embodied-aifoundation-modelslarge-language-modelsMITPython
View on GitHub
In plain words

Generate movement paths for robots using language instructions without needing any training data.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
VoxPoser — GitHub preview card
📈 Star history
833822
2026-07-202026-08-31
📈 Track VoxPoser

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

VoxPoser has 833 stars on GitHub. It has been forked 112 times. VoxPoser is written mainly in Python. It has been in active development since 2023. VoxPoser is available under the MIT license. Its main topics are embodied-ai, foundation-models, large-language-models, motion-planning.

Frequently asked questions

What is VoxPoser?

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Is VoxPoser open source?

VoxPoser is an open-source project. It is released under the MIT license.

Is VoxPoser free?

Yes. VoxPoser is free and open source — you can use, modify and self-host it.

What license does VoxPoser use?

VoxPoser is available under the MIT license.

What language is VoxPoser written in?

VoxPoser is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — VoxPoser

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=huangwl18-voxposer)](https://olud.ai/project/huangwl18-voxposer.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.