Voyager is by MineDojo — not by us.
We indexed this project so people can find it. We are not selling it, we host no copy of the code, and we are not affiliated with or endorsed by its authors — get it from them.
Indexed Aug 1, 2026 · 7,106 stars at index time. Maintainers: claiming verifies your identity and unlocks a higher assurance tier. Removal requests are honored.
simulation · for humans & their agents
Voyager
unclaimed listingactively maintainedFreeMIT
An Open-Ended Embodied Agent with Large Language Models
by Open Source Community · New publisher
Every claim on this page is refundable if it is untrue — refund policy.
☆ Save**MineDojo/Voyager** is an open-source project by MineDojo: An Open-Ended Embodied Agent with Large Language Models. Indexed here so it can be found — not resold.
It is free. Get it from the upstream repository: https://github.com/MineDojo/Voyager
From the project's own README (excerpt, reproduced for discovery under its MIT license):
Voyager: An Open-Ended Embodied Agent with Large Language Models
[[Website]](https://voyager.minedojo.org/) [[Arxiv]](https://arxiv.org/abs/2305.16291) [[PDF]](https://voyager.minedojo.org/assets/documents/voyager.pdf) [[Tweet]](https://twitter.com/DrJimFan/status/1662115266933972993?s=20)
https://github.com/MineDojo/Voyager/assets/25460983/ce29f45b-43a5-4399-8fd8-5dd105fd64f2
We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent’s abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3× more unique items, travels 2.3× longer distances, and unlocks key tech tree milestones up to 15.3× faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize.
In this repo, we provide Voyager code. This codebase is under MIT License.
Installation Voyager requires Python ≥ 3.9 and Node.js ≥…
Preview
See what it does before you commit. Previews show behavior, never source code.
01Capabilities
Does
- + Agent directory
- + Task timeline
- + Tool-call history
Doesn’t
- No exclusions declared
02Requirements & stack
Depends on
- → Programmatic API
Credentials needed
None declared
Stack
03Community
No endorsements yetNo verified confirmations yet — be the first.
Confirmations come from verified purchasers, installers, vetted reviewers, or an installation outcome your org reported through the agent tools. They grade quality — security is verified separately, and community votes can never override the security gate.
Sign in to confirm — weight comes from verified usage, not vote count.
04Trust Passport
Full passport →0/0 automated components pass. An automated score is never a security guarantee.
This listing is unclaimed, so publisher identity cannot be verified and it stays below the “verified” tier by design — that is a statement about the listing, not about the project’s quality. Our automated scans still ran; a maintainer who claims it unlocks identity verification.
- publisher identity Publisher status verified; 0 verification(s) on file
- malicious pattern scan No known malicious-behavior patterns detected in reviewed content
- capability contract All 0 observed capability reference(s) match the declared manifest
- agent safety scan No injection patterns in agent-readable content
- provenance No release signature or provenance attestation
- behavioral sandbox Not performed in this environment — requires the production isolated runner (docs/sandbox-requirements.md). No untrusted code is ever executed on the application host.
Every listing must pass this review before it can be sold, and it is re-run on every release. Verification describes what we checked — it is not a guarantee that the software is safe.
05Versions
Full history →| Version | Channel | Released | Notes |
|---|---|---|---|
| 0.0.0 | stable | Aug 1, 2026 | Indexed listing — see the upstream repository for real release history. |