Skip to content

Hermes And Jev Play Minecraft

Minecraft setup where Hermes plans at milestones, Jev picks one bounded harness action per step, and Mineflayer code owns validity and execution with no screenshots.

Stars
10
Language
JavaScript
License
MIT
Published by
Community
Author
teknium1
Last verified
Oct 2026

Hermes Agent plans, Jev (TypeSafe) picks bounded actions, Mineflayer executes: Minecraft with no screenshots or keypresses from a model. Includes the reproduction of rmalde/minecraft-agent's Ender Dragon run.

Forks
2
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Hermes Agent plans. Jev (TypeSafe's System-One model) picks one bounded action at a time. A Mineflayer harness decides which actions are valid and executes them. No screenshots, no keypresses, no generated code from any model.

Quoted from the project's README. Read the full README.

Highlights

  • Runs a pure-Node 1.16.5 server with one bot and an observe, options, act, and plan API.
  • Logs every plan and Jev decision with probabilities, confidence, cost, and latency.
  • Fixes bad behavior by changing offered options rather than prompt wording.
  • Supports Hermes-only control for watching and Jev control for fast runs.

Watch out

Needs Node, a logged-in Hermes install, and an OpenRouter key for the Jev controller; the original video was not reproduced with its macOS-only recorder. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

16GitHub stars
Free hands-on course of 12 notebooks that pairs Jev decisions with LLM writing across 13 small tools, needing one OpenRouter key and printing cost and self-checks per lesson.
Jev Practices & Patterns#community#awesomejev#catalog-import
6GitHub stars
Watch Jev play chess against OpenRouter LLMs or Stockfish, or play Jev yourself, with every weighed move, likelihood, clock, and finished game saved for replay.
Jev Practices & Patterns#community#awesomejev#catalog-import
5GitHub stars
Inline verifier that checks LLM responses and agent plans with one Jev call across alignment heads and returns block, flag, or pass for gates and hooks.
Jev Practices & Patterns#community#awesomejev#catalog-import
7GitHub stars
Four read-only MCP tools that rank files, cut a file down to the relevant part and pick from long lists, measured on a frozen SWE-bench Lite split.
Jev Practices & Patterns#community#awesomejev#catalog-import
4GitHub stars
Python library and CLI that moves bulk semantic judgments — ticket triage, stale-file tagging, bug or question routing — out of the agent's context into typed Jev questions, with a measured comparison against an in-context control.
Jev Practices & Patterns#community#awesomejev#catalog-import
4GitHub stars
A DSH plugin, published to npm, that registers one agent tool, jev_decide, so a coding agent can ask TypeSafe's Jev a typed question and get a calibrated probability instead of guessing from intuition.
Jev Practices & Patterns#community#awesomejev#catalog-import

From the Jev guides

Original write-ups on what this entry is for.

Most Jev accuracy problems are state problems. What belongs in a state, what is a pre-made judgment to leave out, and why naming the slice you ask about matters more than the wording.
Jev Practices & Patterns#state#design#primitives
Read article
A Noul returns one number and no separate confidence. How to read the value, pin its boundary with criteria, split compound questions, and set a per-action threshold that matches the cost of being wrong.
Jev Practices & Patterns#noul#primitives#confidence
Read article
A Score is a weighted position, not a ruler. Why the number can land between levels, why levels are judged separately, and how to combine several atomic scores in code instead of one crowded rubric.
Jev Practices & Patterns#score#primitives#scoring
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai