Does Auto send my code and files to TypeSafe?

Only your typed prompt bounded by maxPromptChars plus candidate IDs and descriptions go to Jev; file contents, history, tool outputs and stored credentials stay local.

What happens when Jev is unreachable or unsure?

It uses your configured fallback when available, otherwise the turn is not sent and you get an explicit error instead of a silent wrong-model call.

Why must candidate models already be connected?

Candidates must already be authenticated in OpenCode because Auto verifies them against the live catalog and Jev can only choose among eligible models.

Does Auto stay selected after resume or reload?

No. The picker re-hydrates from the last turn's real model after reload or navigation, so reselect Auto to keep routing subsequent turns.

How do I configure the opencode-auto-jev API key?

Only through the plugin's apiKey option; there is no environment-variable support, and it pins the TypeSafe base URL so TYPESAFE_BASE_URL cannot redirect the request. OpenCode {file:...} references let you keep the key in a private file instead of inline.

Does opencode-auto-jev call Jev when only one candidate is eligible?

No. If just one configured candidate is available for a prompt, it selects it deterministically and does not call Jev, because a one-label choice carries no routing information.

What does opencode-auto-jev send to Jev each turn?

The text you typed, bounded to maxPromptChars default 4000, plus each candidate's providerID/modelID and description; file contents, listings, attachments, history, tool outputs, the system prompt and stored credentials are never sent.

CommunityJev Integrations & Adapters

Opencode Auto Jev

OpenCode plugin adding an Auto virtual model that asks Jev to pick one of your connected models per turn, failing closed to a fallback when unsure.

See highlights

Open github.com

Stars: 5
Language: TypeScript
License: MIT
Published by: Community
Author: jorgefspereira
Last verified: Oct 2026

jorgefspereira/opencode-auto-jev

User repository on GitHub

View on GitHub

OpenCode plugin that adds an Auto (Jev) virtual model which routes each prompt to a configured real model using TypeSafe AI (Jev).

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

An OpenCode plugin that adds an Auto (Jev) virtual model to the normal model picker. When you pick Auto, each of your turns is sent to TypeSafe AI (Jev), which picks one of your configured real models for that prompt. OpenCode then calls that real model as usual — native credentials, auth adapters, streaming, tools and accounting all keep working. There is no OpenCode fork and no UI patch. The plugin only: registers a virtual provider/model (auto-jev/auto, displayed as Auto (Jev)) through the config hook, and.

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

Tagscommunity github

Works forJev for Routing

Used inJev for Software & DevTools

Languages: TypeScript

Highlights

Registers a virtual Auto provider without forking OpenCode or patching UI.
Routes once per user turn and leaves manually selected models untouched.
Verifies candidates against the live catalog with modality and tool filtering.
Fails closed to fallback or explicit error with confidence and timeout controls.

Watch out

Each Auto turn adds a Jev request and prompt text is shared with TypeSafe; avoid typing secrets into Auto turns. 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

omp-plugin-jev-router

Oh My Pi extension that asks Jev whether each interactive prompt is simple or advanced, then switches the OMP model role and thinking level without rewriting the prompt.

Jev Integrations & Adapters#community#github

Community

atulify/omp-plugin-jev-routerTypeScript

SiYuan

46.7k

Privacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.

Jev Integrations & Adapters#community#note-taking#knowledge-base

Community

siyuan-note/siyuanTypeScript

Sim

29.8k

Open-source workspace with 29,796 stars for building, deploying and monitoring AI agents and workflows -- visual builder, chat, tables, files and knowledge -- featuring native TypeSafe System One evaluation and decision provider integration.

Jev Integrations & Adapters#community#agents#workflow-automation

Community

simstudioai/simTypeScript

Eliza

19.6k

Open-source TypeScript agentic operating system: a core runtime, app for web and mobile, CLI, cloud services and first-party plugins. The directory's curated summary reports it integrates TypeSafe System One decision services for sub-100ms intent classification, action dispatching and confidence-gated tool execution.

Jev Integrations & Adapters#community#agents#framework

Community

elizaOS/elizaTypeScript

Inbox Zero

12.4k

Open-source AI email assistant (Next.js, Postgres, 12k+ stars) with a decision-model layer that can run on openrouter:typesafe/jev-1.13: Jev-backed questions cover rule selection, cold-email detection, thread status, recurring patterns, unsubscribe pages, and sender categorization, each with evals.

Jev Integrations & Adapters#community#email#gmail

Community