DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Jev Harness

JevHarness is a Python project where an LLM writes a task-specific harness, meaning code and Jev judgment questions that turn task observations into actions, with optional reward-based reflection to improve it.

Trended earlier

TianyuCodings/JevHarness on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Draft a task-specific harness in Claude Code

    Install the Jev Harness plugin and have Claude Code draft a Jev decision harness for your task.

    View prompt
    Using the JevHarness repo at https://github.com/TianyuCodings/JevHarness, invoke the jev-harness skill to draft a harness that routes <ticket type> to the right team. Ask for inputs, legal actions, examples, success criteria, and budget before writing any code. Expected output: a plan listing those items. Verify that every legal team action appears in the plan.

  • Inspect the Pokémon harness archive locally

    Run the bundled Pokémon example viewer to review decisions without making any model requests.

    View prompt
    Clone https://github.com/TianyuCodings/JevHarness, build and preview the website with Node.js on port 8768, then report the number of archived Eval games shown on the page. Expected output: the viewer loads at localhost:8768. Verify that browsing makes no model requests and starts no games.

  • Install the Jev Harness skill in Codex

    Add the jev-harness skill to Codex and use it to plan a harness for your task.

    View prompt
    In Codex, install the jev-harness skill from https://github.com/TianyuCodings/JevHarness and then run it on the task: route <ticket type> to the right team. Expected output: a list of clarified inputs, legal actions, examples, and success criteria. Verify that the skill is discovered before the task is sent.

  • Improve a harness with reliable rewards and reflection

    Use reward-based evaluation and GEPA reflection to evolve a harness from full execution traces.

    View prompt
    Using the JevHarness skill from https://github.com/TianyuCodings/JevHarness, plan an evaluation and reflection loop for <task> with a trusted reward, a training batch, and an Eval set. Expected output: a plan naming the selection split, the reflection inputs, and how accepted proposals are checked on Eval. Verify that the plan keeps Eval separate from the reflection inputs.

How to use Jev Harness

  1. Check you have what it needs: Claude Code or Codex installed; Git, and Node.js for the local archive viewer; Access to Jev model calls, since plugin installation does not configure model keys.
  2. Open TianyuCodings/JevHarness on GitHub and read the README and license.
  3. Run /plugin marketplace add https://github.com/TianyuCodings/JevHarness.git inside Claude Code.
  4. Run /plugin install jev-harness@jevharness.
  5. Run /reload-plugins.
  6. Run /jev-harness:jev-harness with your task, and answer its questions about inputs, legal actions, examples, success criteria, and budget.

These steps come from our top use case, Draft a task-specific harness in Claude Code, which also has a copy-paste agent prompt.

Jev Harness alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • Claude Code or Codex installed
  • Git, and Node.js for the local archive viewer
  • Access to Jev model calls, since plugin installation does not configure model keys
  • A Python environment if you plan to build and run a harness yourself
Maintain Jev Harness? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/tianyucodings-jevharness.svg)](https://dedupedai.com/use-cases/tianyucodings-jevharness/?ref=badge)

More badge styles and HTML

Questions about Jev Harness

What is Jev Harness?

JevHarness is a Python project where an LLM writes a task-specific harness, meaning code and Jev judgment questions that turn task observations into actions, with optional reward-based reflection to improve it. It is an open-source project on GitHub: https://github.com/TianyuCodings/JevHarness.

Who is Jev Harness for?

Developers and AI agent builders who want an LLM to design a fixed decision harness that later runs on fast Jev calls.

What can I do with Jev Harness?

4 use cases so far, for example: Draft a task-specific harness in Claude Code; Inspect the Pokémon harness archive locally; Install the Jev Harness skill in Codex. Each has steps and a copy-paste agent prompt.

What do I need to run Jev Harness?

Claude Code or Codex installed; Git, and Node.js for the local archive viewer; Access to Jev model calls, since plugin installation does not configure model keys; A Python environment if you plan to build and run a harness yourself.

What are alternatives to Jev Harness?

Other hot AI repos in Software and DevOps: Harness2, iFixAi, Orca, Diagram Design, AI Memory.

Is Jev Harness safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.