# microsoft/PromptCraft-Robotics

Community for applying LLMs to robotics and a robot simulator with ChatGPT integration

Repository: https://github.com/microsoft/PromptCraft-Robotics
Canonical: https://ross.abutalabs.com/products/promptcraft-robotics
Homepage: https://aka.ms/ChatGPT-Robotics
Language: Python
License: MIT
License Family: permissive
Topics: airsim, chatgpt, llm, prompt-engineering, robotics, simulation
Last push: 2024-01-20T20:38:07+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 93
- inputs: {"age_days": 1303, "days_push": 956, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2115, forks 222 (observed 2026-08-28T04:06:15.885125+00:00)

## What it is
A Microsoft community repository for collecting and sharing LLM prompting examples for robotics tasks, plus a sample robot simulator built on AirSim with ChatGPT integration. It accompanies the 'ChatGPT for Robotics' research paper.

## Use cases
- find prompt examples for controlling robots with LLMs
- try ChatGPT integration with an AirSim drone simulator
- learn how to apply large language models to robotics
- contribute robotics prompts to a community collection
- reproduce ChatGPT for Robotics research experiments

## When to choose
- you want curated LLM prompting examples for robotics domains like manipulation or home robotics
- you want a ready-made simulator to experiment with ChatGPT-driven robot control
- you want to follow the Microsoft ChatGPT for Robotics design principles

## When to avoid
- you need a production robotics control stack
- you want a maintained library with stable APIs rather than example prompts and a demo simulator
- you need support for non-OpenAI LLMs out of the box

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: prompt-engineering, simulation, agent-framework
- domain: robotics, artificial-intelligence, large-language-models, simulation
- platform: python, cross-platform
- tags: chatgpt, airsim, robot-simulator, community, llm-examples

## Member repositories
- microsoft/PromptCraft-Robotics (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:15.885125+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:53:21.974050+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/PromptCraft-Robotics (fetched 2026-08-28T04:06:15.885125+00:00, sha 4175337d0b16)
- Data as of 2026-08-30T08:39:29.467469+00:00.