Skip to content

OpenDecision

An Apache-2.0 decision engine with a TypeSafe-compatible endpoint, document answers with source passages, and a ViZDoom demo that picks actions from structured game state.

Category
Models & Reimplementations
Format
—
Published by
Community
Author
deepanwadhwa
Added
2026-09-28
Last verified
2026-09-28

Highlights

  • Question types are Choice, Score, Noul, and Relation: supports, contradicts, unknown, or conflicted.
  • A TypeSafe SDK compatible endpoint is part of the API surface, alongside a Python API and a FastAPI server.
  • The Doom demo reads health, ammo, kills, positions, and recent damage. The recordings are fixed-seed, and no win rate is measured.
  • The document API splits long documents and returns the passages it used. A GDPR retrieval set answers 9 of 10 objective questions.

Quickstart

bash
opendecision serve

Watch out

Apache-2.0. The README calls it a developer preview and says to treat scores as uncalibrated until you fit thresholds on your own data. Not affiliated with TypeSafe.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

More like this

1.1kGitHub stars
A local yes/no decision model that speaks Jev's wire format on a laptop CPU, refusing Choice and Score until those question types ship.
Models & Reimplementations#community#python#open-models
689GitHub stars
A local server that reads next-token probabilities from a fine-tuned Spark model and returns Choice, Score, and Noul answers with zero generated tokens.
Models & Reimplementations#community#python#open-models
39GitHub stars
A local /v1/systemone server that reads label probabilities from a GGUF chat model, with prompt repetition and a confidence shrink toward uniform.
Models & Reimplementations#community#python#open-models
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Agent Handoff Gate: agents verify what they hand off

A local Telegram analyzer with Jev as the classifier

I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • jevclassifier.vercel.app Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

A Krunker-inspired FPS, decided by Jev

Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

Pixel art out of 256 multiple-choice questions

I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…

Image
Image
Image
Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

An Elixir port of the official SDK

jod: Zod validates data, Jev judges it