# mindcraft-bots/mindcraft

Minecraft AI with LLMs+Mineflayer

Repository: https://github.com/mindcraft-bots/mindcraft
Canonical: https://ross.abutalabs.com/products/mindcraft
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2026-06-10T14:58:17+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 86, release rhythm 75, longevity 79
- inputs: {"age_days": 1113, "days_push": 84, "days_rel": 166, "gap_med": 13.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5680, forks 901 (observed 2026-08-28T04:09:27.804876+00:00)

## What it is
Mindcraft is a JavaScript application that connects LLM-powered AI agents to Minecraft via the Mineflayer library, letting language models control in-game bots. It supports multiple LLM API providers and includes a MineCollab task framework for multi-agent collaboration.

## Use cases
- run an LLM-powered bot in Minecraft
- build AI agents that play Minecraft
- research multi-agent collaboration in games
- let a language model control a Minecraft character
- experiment with embodied AI agents
- create AI companions in a Minecraft world

## When to choose
- you want LLM-driven bots in Minecraft Java Edition
- you're doing research on agent collaboration or embodied AI
- you want a hackable Node.js codebase for game agents

## When to avoid
- you need Bedrock Edition support
- you can't expose LLM API keys or run Node.js
- you need a hardened sandbox - code execution has injection risks

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, chatbot, game
- domain: gaming-tools, large-language-models
- platform: cross-platform, game-engine
- tags: minecraft, mineflayer, llm-agents, bot, game-ai, ai-agents, automation, nodejs

## Member repositories
- mindcraft-bots/mindcraft (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.804876+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 2026-08-29T17:54:15.611078+00:00, confidence not recorded.
  - readme: https://github.com/mindcraft-bots/mindcraft (fetched 2026-08-28T04:09:27.804876+00:00, sha 4004764c3138)
- Data as of 2026-08-30T08:39:29.467469+00:00.