krzysztof-cieslak/jev-agent-control
User repository on GitHub
OpenCode V2 agent routing and autonomous handoffs powered by Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Jev Agent Control
An OpenCode V2 server plugin that uses Jev to route requests between the Plan, Build and your own primary agents, and hand off unfinished work at completed execution boundaries while following each target agent's configured model.
- Stars
- 3
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Krzysztof-Cieslak
- Last verified
- Oct 2026
- Languages
- TypeScript
- Capabilities
- Open sourceRequires API key
Highlights
- OpenCode V2 server plugin that routes requests between Plan, Build and your own primary agents using Jev.
- Hands off unfinished work at completed execution boundaries and follows each target agent's configured model.
- Install from npm by adding opencode-jev-agent-control to the plugins array of opencode.jsonc; OpenCode installs it automatically.
- Options include enabled and autoHandoff; local installs clone the repo and run npm ci and npm run build with Node.js 20+.
- Requires OpenCode V2 and is tested with 2.0.24; the README points to a TypeSafe account for the API key.
Quickstart
bash
git clone https://github.com/Krzysztof-Cieslak/jev-agent-control.git
cd jev-agent-control
npm ci
npm run buildWatch out
README and GitHub metadata reviewed 2026-10-17; the excerpt truncates inside the local-install JSON example, so the complete option list and the API-key flow are not evidenced. MIT license; created and pushed 2026-10-09.
Questions about this entry
Short answers drawn from the linked project or page.
An OpenCode V2 server plugin that uses Jev to route requests between Plan, Build and your own primary agents, and to hand off unfinished work at completed execution boundaries while following each target agent's configured model.
The README says the plugin uses Jev to route requests between the agent roles. It documents the behavior rather than the prompt or call shape, and links docs.typesafe.ai for Jev itself.
When an execution boundary is completed, the plugin hands unfinished work to another agent instead of stopping, and the target agent continues with its own configured model. The autoHandoff option controls this behavior.
For npm releases, add the opencode-jev-agent-control package to the plugins array in your project's opencode.jsonc and OpenCode installs it automatically. For unreleased changes, clone the repo and run npm ci and npm run build with Node.js 20 or newer.
OpenCode V2, tested by the author with OpenCode 2.0.24, and a connected TypeSafe account so the plugin can call Jev. The README links an API-key section for that connection.
Krzysztof Cieslak publishes it under the MIT license; GitHub metadata shows 3 stars, created 2026-10-09 and last pushed the same day.
The excerpt truncates inside the local-install JSON example, so the full option list beyond enabled and autoHandoff and the exact API-key flow are not evidenced, and no benchmarks or costs are shown.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: OpenRouter Decision Model Rankings
X: herdr + jev, an agent router
X: A group chat bot with decision room routing
More Jev resources like this
A Claude Code plugin that picks Haiku, Sonnet or Opus and a reasoning effort for every prompt, step and subagent, with an effort cap, a prompt-cache guard and a status band; the repo is named jev-router and tagged typesafe.
Jev Integrations & Adapters#community#github#typescript
Community
dominicrico/jev-routerTypeScript
dominicrico/jev-routerTypeScriptA Claude Code mod that sends each prompt to Jev through OpenRouter and turns the returned 0-3 score into a reasoning effort level, from low to xhigh. Shadow mode is on by default, so it only logs what it would set until you turn it off.
Jev Integrations & Adapters#community#github#claude-code
Community
gebeer/jev-effortTypeScript
gebeer/jev-effortTypeScriptA DeepSeek Harness plugin that lets the agent switch model presets and thinking depth on its own, either with the set_model and switch_preset tools or through Jev, which reads each turn's instruction and picks a tier. Jev auto-switching is a separate switch, off by default.
Jev Integrations & Adapters#community#github#deepseek
A router that asks a classifier, Jev by default, how much reasoning each step of a coding session needs, then adds that effort to the model request without breaking the prompt cache. It ships as an OpenCode plugin, a Pi extension and a local proxy for Codex CLI.
Jev Integrations & Adapters#community#github#routing
System One routing for coding agents where Jev decides and the LLM generates: an OpenCode v2 plugin, Cursor hooks and a skill cover turn steering, tool-call redirects, permission gating, failure advice, subagent routing, code review and on-demand jev_ask decisions.
Jev Integrations & Adapters#community#github#opencode
Community
drmaas/jev-routerTypeScript
drmaas/jev-routerTypeScriptA Claude Code plugin that asks Jev, TypeSafe's System One model, which model tier each prompt needs — haiku, sonnet or opus — and switches automatically, and routes classification, scoring and yes/no judgments to Jev via scripts/jev.py.
Jev Integrations & Adapters#community#github#claude-code
Community
ricky94511/jevTypeScript
ricky94511/jevTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.