mrkeyoor.comAsk

rmalde/minecraft-agenttested 07 Oct 2026commit 78b40ed

minecraft-agent review

Inspect Minecraft Agent if your question is how a surveyed route, planner, bounded selector, and game executor fit together.

  • Install 133 s
104/109passed, run exited non-zero
  • 266 packages
AI Toolsevaluationupdated 24 Oct 2026
+2stars / 7d

Minecraft Agent is a JavaScript Minecraft Java 1.16.5 experiment that combines Astra or Sol planning, JEV action selection, and Mineflayer execution on a fixed, surveyed route. It is useful for studying bounded model control. The supplied evidence does not establish general play on unknown worlds or isolate the models' contribution to completion.

Verdict

Inspect Minecraft Agent if your question is how a surveyed route, planner, bounded selector, and game executor fit together. Budget for substantial configuration before trying a full run. Our October 7, 2026 dependency installation succeeded at commit 78b40ed, while the recorded test command reported 104 passes and 5 failures. That warrants investigating the failures before adoption; it does not prove the game controller is broken. The README's successful demonstration remains an upstream report, and the supplied evidence does not establish general-world autonomy or the models' causal contribution.

We ran it

Lab card: what happened when we ran minecraft-agent
Lab card from our sandbox run
Screenshot of minecraft-agent (github.com/rmalde/minecraft-agent)
github.com/rmalde/minecraft-agent
Install✓ · 133s266 packages · 1268 MB
Buildn/ano build script
Tests✗ · 7s104 passed · 5 failed of 109 (node:test)
Known vulns60 critical · 0 high · 6 moderate · 0 low (npm audit)
Repo238 files~2,894 lines of source · 5.9 MB · 0 CI workflows

Answers from our run

Does minecraft-agent build from source?

Dependencies installed in 133 seconds (266 packages), and the project has no separate build step. We cloned commit 78b40ed into a clean Debian container with 3 CPUs and no project-specific setup.

Do minecraft-agent's tests pass?

No. The project's own test command finished in 7 seconds and reported 104 passed, 5 failed (node:test).

Does minecraft-agent have known vulnerabilities in its dependencies?

npm audit flagged 6 known advisories in the dependency tree at the time of our run.

Who should not use minecraft-agent?

Players expecting an agent that discovers an unknown world: the supplied route includes known resource and portal coordinates.

What are the alternatives to minecraft-agent?

Voyager, Mineflayer. Inspect Minecraft Agent if your question is how a surveyed route, planner, bounded selector, and game executor fit together.

Setup1/5Full reproduction requires Minecraft, native capture tooling, credentials, and configured local services; our October 7, 2026 run verified dependency installation and test execution only.
Docs4/5The supplied README explains model roles, surveyed-route assumptions, credentials, recording, and verification limits; documentation is not independent verification of its reported run.
Community1/5The supplied issue shows external discussion, but contributor breadth and support responsiveness are not established. This is an evidence limitation, not proof of an inactive community.
Maturity2/5The manifest is version 0.1.0 with several latest dependencies; the dated scan detected no CI workflows, and the recorded test command reported five failures with unresolved causes.

Who it’s for

Agent researchers studying planning and bounded action selection.
Mineflayer developers inspecting route navigation, inventory handling, and dragon combat.
Experimenters prepared to configure Minecraft, model credentials, and a native recording client before attempting reproduction.

Who it’s NOT for

Players expecting an agent that discovers an unknown world: the supplied route includes known resource and portal coordinates.
Developers requiring a green recorded test command before adoption: our October 7, 2026 run at commit 78b40ed reported failures whose causes are not shown in the retained tail.
Users expecting a portable one-command demonstration: the README describes macOS-developed launch scripts and machine-specific configuration.
Reviewers expecting the named demonstration's recordings and generated evidence inside the clone.

Setup reality

In our recorded run on October 7, 2026 at commit 78b40ed59514e5e2abde33a05ce398ecb2c39e05, dependency installation exited successfully after approximately 133 seconds. The stored dependency metric is 266 packages and 1,268 MB; the npm installation tail separately says it added 228 packages. These are different recorded counts, so 266 must not be described as packages added by npm.

The build step was skipped because there was no build script. The test command exited 1 after approximately 7 seconds. Its retained runner summary reported 104 passed, 5 failed, and 0 skipped, with 109 tests reported overall. These counts are recorded runner output, not independently reconciled exhaustive unique coverage. The retained tail does not identify the five failure causes.

The stored npm audit result reports 6 moderate advisories, with 0 high, critical, or low. Audited-package coverage is unknown; neither the dependency metric nor the installation tail establishes it. These results do not establish safety.

The README's full-run instructions additionally require a Minecraft Java 1.16.5 server, a compatible server runtime, Python, the supplied native client's Java 17 runtime, and a built display/capture adapter. Model access needs OpenRouter credit and Google application default credentials with Secret Manager access. Configure the original project and secret references, runtime paths, and local services. Dependency installation alone does not demonstrate a working agent, installed CLI, native client, recording pipeline, or completed game.

What this experiment can tell you

Minecraft Agent puts model decisions inside a surveyed Minecraft route. That makes it a useful controller case study, but limits what a successful demonstration can establish.

The supplied configuration specifies Minecraft Java 1.16.5, Peaceful difficulty, and seed 8398967436125155523. It includes the village, three supply chests, eight preparation beds, Nether waypoints, and active End portal coordinates. The README says the route was surveyed in a separate test world and that known coordinates are supplied. Reproducing this route therefore would not establish discovery or planning ability on an unknown seed.

The README identifies openai/gpt-6-astra as the default planner, with openai/gpt-5.6-sol as an option, and typesafe/jev-1.13 as the action selector. The planner sets objectives, item targets, and waypoints. JEV selects an available action from structured observations. Mineflayer handles pathfinding and game protocol interactions. This is structured-state control rather than screenshot-only or individual-key control.

Separate completion from model contribution

The README reports that nether-final-08 completed in 8 minutes 43.300 seconds, using 131 JEV decisions and 35 Astra calls. It describes an empty-inventory start in a fresh Survival/Peaceful world, six bed explosions during the first dragon landing, full health at the exit, and no deaths or operator repairs. Those are the author's reported results. Our sandbox did not reproduce that workload or inspect its local recording.

The README also reports 17 run checks, eight route/camera/screen checks, and 29 local tests passing. Those checks belong to its account of the demonstration; they are separate from our recorded test command below.

A completion demonstrates the combined controller under its stated conditions. It does not, by itself, identify what changes when Astra or JEV is removed. Issue 4 contains a contributor's account of modified-controller experiments and requests repeated comparisons with simpler selectors. The supplied issue text does not provide a reconciled dataset sufficient to quantify that contribution. Its accusations and reproduction claims should not be treated as our findings.

What our recorded run actually established

Our stored run is dated October 7, 2026 at commit 78b40ed59514e5e2abde33a05ce398ecb2c39e05. The recorded sandbox configuration was 3 CPUs, 8 GB of memory, and image lab-node:22. The image label alone does not verify the actual runtime version.

Dependency installation exited successfully after approximately 133 seconds. The stored dependency metric records 266 packages and 1,268 MB. The installation tail says npm added 228 packages. We retain both observations without treating them as interchangeable counts. The manifest identifies package version 0.1.0; several direct dependencies use latest, so the commit alone does not pin those dependency versions.

The build step was skipped because no build script was available. This is neither a successful build nor a failed build.

The test command exited 1 after approximately 7 seconds. Its retained summary reports 104 passed, 5 failed, 0 skipped, and 109 tests overall. These are recorded runner counts. No new execution or complete-log reconciliation established exhaustive unique test coverage. The retained tail does not show the five failing assertions, so it cannot establish whether they arose from code, dependencies, environment, or another cause. A failed test command is not proof that the gameplay demonstration cannot work.

The stored npm audit result reports 6 moderate advisories and 0 high, critical, or low. Audited-package coverage is unknown. This is a dated dependency advisory result, not a security review of the controller or proof of safety.

The repository scan recorded 238 files, approximately 2,894 source lines, and 5.9 MB, with no detected CI workflows, Dockerfile, Compose configuration, or separate tests directory. The README does document tests alongside modules. A missing separate tests directory does not mean tests are absent, and the scan does not establish branch-protection settings.

What a full reproduction still needs

The README requires more than npm install: a Minecraft Java 1.16.5 server, a compatible server runtime, Python tooling, the native client's Java 17 runtime, and a compiled display/capture adapter. Model calls require OpenRouter credit. The documented credential path uses Google application default credentials and Secret Manager; the original project and secret references need configuration for your account.

The native renderer and launch scripts were developed on macOS. That establishes a setup assumption, not incompatibility with Linux or Windows. Runtime paths and local server settings need adjustment on another machine.

The documented services include the main server on port 25576, status on 3078, dragon sensor on 3093, and model relay on 3099. A fresh recording requires an unused world name and matching new log directory. A new log directory alone does not reset the world.

Our dependency installation and test execution did not establish that the server, model calls, native client, recorder, or gameplay worked. The README explicitly says live server tests remain necessary for movement, crafting, combat, and recording.

Evidence to request before relying on the demonstration

The README says recordings and generated evidence remain local and are excluded from Git. It also excludes Minecraft binaries, downloaded runtimes, saved worlds, and credentials. The clone therefore cannot supply the complete evidence for the named run on its own.

Its documented verification process combines requests and game events in events.jsonl, dragon-death evidence, an exit-portal event, a world-state check, and video review. Prepared combat-lab trials are explicitly separate from full Survival runs. These are useful verification requirements, but documenting them is different from independently checking the artifacts.

Before adoption, reproduce the test command and inspect its failures. Before crediting the models with the completion, request the named run's raw evidence and repeated controller comparisons under matched conditions. Before claiming portability, exercise the full server and recording stack on the intended platform.

How to read the scores

These are editorial readiness ratings, not benchmark results. The scale is 1 for substantial unresolved requirements or insufficient supporting evidence, 2 for a usable starting point with major gaps, 3 for adequate documented support, 4 for detailed support with explicit limits, and 5 for support corroborated across the relevant use cases. Unknown adoption or compatibility earns no assumed credit. Each category rates a different question, so the scores should not be averaged into an overall quality claim.

Setup scores 1 because the full reproduction requires several configured services and was not exercised in our run. Documentation scores 4 because the README explains model roles, route assumptions, credentials, recording, and verification limits. Community scores 1 because the supplied material does not establish contributor breadth or support responsiveness. Maturity scores 2 because the manifest is version 0.1.0, several direct dependencies use latest, the scan detected no CI workflows, and the recorded test command has unresolved failures.

Which alternative fits your question?

Voyager is relevant when you want to study an exploration curriculum and reusable executable skills. Its README describes those components; we did not reproduce its capability claims.

Mineflayer is relevant when you want a JavaScript bot API and will build the controller yourself. It is already part of Minecraft Agent's stack, so this choice means taking responsibility for the planning and execution design rather than replacing the demonstration with an equivalent packaged agent.

Alternatives

ProjectWhat it isPick it when
VoyagerA Minecraft research agent whose README describes an exploration curriculum, executable skill library, and iterative prompting.Choose it to study exploration and reusable skill acquisition rather than reproduction of this fixed route. Its reported capabilities are upstream claims, not results from our sandbox.
MineflayerA JavaScript API for building Minecraft bots, also used by Minecraft Agent.Choose it as the foundation for your own bot when you want to define the controller yourself. It is a framework alternative, not a ready replacement for this model-controlled demonstration.

What people are saying

  1. [velocity-scout] rmalde/minecraft-agent

Sources

  1. Minecraft Agent README at commit 78b40ed
  2. Minecraft Agent package manifest at commit 78b40ed
  3. Fixed Nether route configuration at commit 78b40ed
  4. Open issue 4 on controller contribution and ablation
  5. Minecraft Agent GitHub repository

More ai tools reviews