Skip to content

Codriver

Per-turn opencode router that asks Jev which fleet model fits the turn, rewriting to that model or falling back on low confidence.

Stars
0
Language
TypeScript
Published by
Community
Author
johnpozy
Last verified
Oct 2026

johnpozy/codriver

User repository on GitHub

View on GitHub

Instead of locking a whole session to one model, you pick Auto in the model picker — and for every turn, Codriver asks Jev (TypeSafe AI's non-generating "System One" decision model) which concrete model from your fleet fits THIS turn, then rewrites the message to that model before it is sent.

Forks
0
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Codriver is a per-turn model-routing plugin for opencode. Instead of locking a whole session to one model, you pick Auto in the model picker — and for every turn, Codriver asks Jev (TypeSafe AI's non-generating "System One" decision model) which concrete model from your fleet fits THIS turn, then rewrites the message to that model before it is sent.

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

Highlights

  • Adds codriver/auto picker; each Auto turn makes one Jev call and rewrites to the chosen fleet entry before sending.
  • Falls back on low confidence under 0.55, timeout over 1500ms, error, or missing key; config re-reads every turn.
  • Shares one fleet file outside agent config; starter fleet prefers custom providers then built-in coding defaults.
  • Proxy mode keeps picker on Auto via loopback gateway, forwarding upstream and piping streaming response untouched.

Watch out

Needs opencode with reachable provider models; unset key uses deterministic fixture client with canned decisions. 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

1GitHub stars
Voice-driven UI prototyper for Next.js: local whisper.cpp transcribes mic audio on the Mac, Jev answers a batch of typed Choice/Noul questions per utterance, and json-render renders the design as shadcn/ui React.
Jev Models & Reimplementations#community#github
Local-first web app that pulls a repo issues and README, asks Jev to score complexity, criticality, effort and relevance, then sorts and exports.
Jev Models & Reimplementations#community#github
0GitHub stars
No-code layer that turns plain English into validated Jev schemas, confirming with chips before deterministic execution and verdict card.
Jev Models & Reimplementations#community#github
823GitHub stars
A local Jev-compatible POST /v1/systemone server in TypeScript that maps typed questions onto oMLX classification prompts and normalizes logprob-style answers.
Jev Models & Reimplementations#community#typescript#local
174GitHub stars
Express and Vite playground for System One-style decisions, taking a state plus typed questions and returning structured answers. Three swappable backends: per-option LLM micro-scorers, one structured JSON call, or a locally served decider model.
Jev Models & Reimplementations#community#jevbest
Native Swift 6 package that evaluates @Generable structs and enums through System One decision models in 15-150 ms, with on-device Laya, self-hosted laya-serve, and TypeSafe Jev cloud backends.
Jev Models & Reimplementations#community#github

From the Jev guides

Original write-ups on what this entry is for.

Jev takes text only; Clef-omni adds image, audio, and video input and Liquid d1 adds images, each keeping the same typed-answer shape. Where that matters, where it does not, and the costs the vendors underplay.
Jev Models & Reimplementations#multimodal#open-models#decision-model
Read article
One model in September, a dozen by October. Clef, Liquid d1, Perplexity, and OpenAI all ship the same typed-answer shape now. How to read the rival benchmarks and pick on your own task.
Jev Models & Reimplementations#decision-model#benchmarks#pricing
Read article
Hundreds of repositories carry the system-one tag, but the ecosystem is a dozen ideas in different sizes. A tour of the families, the licenses, and what a download does not include.
Jev Models & Reimplementations#open-models#hugging-face#local
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai