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

What you can do with RSI Jev

RSI-Jev is a set of typed-decision models (yes/no, pick-one and rubric questions) that AI agents trained in a self-improving loop, with the checkpoints, code and failed experiments published.

Trended earlier

Shanghua-Gao/RSI-Jev 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?

5 use cases

  • Serve a decision model behind a local API

    Run v6.1-VL 4B locally and get calibrated yes/no or pick-one answers over HTTP.

    View prompt
    In the Shanghua-Gao/RSI-Jev repo, install the package with pip, then run `rsi-jev serve v6.1-vl-4b --effort auto --port 8000`. Send the <question> about the text <input> to localhost:8000/v1/systemone and return the probability for each option. Verify that the response includes the layer that answered and a confidence value.

  • Make a typed decision in Python without a server

    Call the Decider class in a script to score options for text or images.

    View prompt
    Using the Shanghua-Gao/RSI-Jev package, write a Python script that loads Decider with v6.1-vl-4b and calls decide() on each record in <input-file> with a noul question about <topic>. Output one line per record with the option probabilities. Verify that every record gets a result and that image inputs are passed only when present.

  • Run the 4B decision model on a Mac

    Serve the MLX build of v6.1-VL 4B on Apple silicon using the MLX backend.

    View prompt
    In the Shanghua-Gao/RSI-Jev repo, install the mlx extras with pip, then run `rsi-jev serve v6.1-vl-4b-mlx-8bit --backend mlx`. Follow docs/mac.md and send one decision request about <question> to the local server. Return the answer and the layer reported. Verify that the server runs on Apple silicon and returns a response without errors.

  • Point an existing Jev client at this server

    Switch a Jev client's base URL to a local RSI Jev server without rewriting code.

    View prompt
    Given an existing Jev client in <project-path>, point its base URL to localhost:8000 after running `rsi-jev serve v6.1-vl-4b --effort auto --port 8000` from the Shanghua-Gao/RSI-Jev repo. Run one existing client request and return the response. Verify that the client works with no other code changes.

  • Check failed experiments before planning a training run

    Read the published failed experiments to avoid repeating dead ends.

    View prompt
    In the Shanghua-Gao/RSI-Jev repo, read EXPLORE.md, docs/history.md and docs/rl.md and list every experiment that relates to <topic>. For each one, return the result and the failure reason as written in the repo. Verify that each item cites the file where it appears.

How to use RSI Jev

  1. Check you have what it needs: Python with pip and git installed; A GPU with enough memory for the chosen model, or an Apple silicon Mac for the MLX builds; A 96 GB GPU if you want to serve the 27B model.
  2. Open Shanghua-Gao/RSI-Jev on GitHub and read the README and license.
  3. Install the package with pip install "rsi-jev[fast,vision] @ git+https://github.com/Shanghua-Gao/RSI-Jev"
  4. Start the server with rsi-jev serve v6.1-vl-4b --effort auto --port 8000
  5. Send a test question with curl localhost:8000/v1/systemone -H 'Content-Type: application/json' -d '{"model": "jev-latest", "state": "I was charged twice. Please refund.", "questions": {"refund": {"type": "noul", "instructions": "Does the user request a refund?"}}}' (inferred, check the README)
  6. Check that the response reports the layer that answered and its confidence

These steps come from our top use case, Serve a decision model behind a local API, which also has a copy-paste agent prompt.

RSI Jev alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forBuilt for developers who want a fast, calibrated decision model they can serve locally, and for researchers who want to see what the loop tried and why it failed.
  • Why it is hot
  • LanguageHTML
  • Sourcegithub.com/Shanghua-Gao/RSI-Jev · Back to Hot repos

Requirements

  • Python with pip and git installed
  • A GPU with enough memory for the chosen model, or an Apple silicon Mac for the MLX builds
  • A 96 GB GPU if you want to serve the 27B model
Maintain RSI Jev? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/shanghua-gao-rsi-jev.svg)](https://dedupedai.com/use-cases/shanghua-gao-rsi-jev/?ref=badge)

More badge styles and HTML

Questions about RSI Jev

What is RSI Jev?

RSI-Jev is a set of typed-decision models (yes/no, pick-one and rubric questions) that AI agents trained in a self-improving loop, with the checkpoints, code and failed experiments published. It is an open-source project on GitHub: https://github.com/Shanghua-Gao/RSI-Jev.

Who is RSI Jev for?

Built for developers who want a fast, calibrated decision model they can serve locally, and for researchers who want to see what the loop tried and why it failed.

What can I do with RSI Jev?

5 use cases so far, for example: Serve a decision model behind a local API; Make a typed decision in Python without a server; Run the 4B decision model on a Mac. Each has steps and a copy-paste agent prompt.

What do I need to run RSI Jev?

Python with pip and git installed; A GPU with enough memory for the chosen model, or an Apple silicon Mac for the MLX builds; A 96 GB GPU if you want to serve the 27B model.

What are alternatives to RSI Jev?

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

Is RSI Jev 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.