Jev Opencode

An opencode plugin (also for pi and Claude Code) that puts every bash command in front of a System One decision model before it runs: a small model scores destructiveness, secret leakage, and your repo's GUARDRAILS.md policy and blocks bad calls.

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.

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.

A plugin and skill for coding agents that guards shell commands, compacts history and adapts thinking effort using any System One decision model: TypeSafe Jev via API, OpenRouter, Vercel AI Gateway, OpenCode Zen or a self-hosted llama.cpp, Ollama or LM Studio server.

An opencode security plugin powered by Jev that risk-scores every tool call before it runs and scans every result for prompt injection afterwards. Deny blocks, ask prompts and allow runs, with configurable thresholds and an optional fail-closed mode.

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.

A classifier that screens shell commands requested by LLM agents before they run: each command goes to an external judgment backend — TypeSafe's Jev is the production default — and the verdict becomes allow, block, or the normal interactive prompt in the OpenCode V2 harness.

OpenCode's Zen gateway serves Jev 1.13 on its own /v1/systemone endpoint with an OpenCode key: jev-1.13 paid and jev-1.13-free for a limited time, documented with noul, choice, and score examples.

OpenChamber is an MIT-licensed workspace built on the OpenCode agent for running and reviewing AI coding work on desktop, web, VS Code, and mobile, with session goals, multi-run comparisons, and private remote access.

An opencode plugin that turns an agent's small decisions — is this command safe, which tool fits, is this PR ready — into typed Jev questions with calibrated confidences, labelling each answer auto or escalate so the agent knows when to ask for help.

An OpenCode plugin that asks Jev how much reasoning each step needs — low for a rename, high for a failing test — and adds the picked effort to the request, falling back to high when Jev is slow or unavailable. Archived and superseded by reasoning-router.

An OpenCode plugin that keeps the session on a cheap sticky parent model so the cache stays warm, and asks Jev whether a turn is hard before escalating through jev_escalate to temporary stronger subagents.

OpenCode V2 plugin monorepo by Ope Oginni, released as independent npm packages: oc-auto-perms brings intent-aware permissions powered by Jev, alongside WIP plugins for iMessage notifications and TUI Invaders.

A local stdio MCP server that adds a jev_decide tool to OpenCode agents, supporting noul, choice and score questions so an agent can route or gate work on structured answers and probabilities instead of prose.

An OpenCode 2 plugin that sends every shell command — local or over FarHand's remote shell — to Jev first: six typed questions about global installs, host litter, harmful actions and privacy, and a permission prompt whenever something looks risky.

An OpenCode V2 plugin that asks TypeSafe Jev whether a prompt is deterministic before the LLM reasons, injecting a JEV PRE-ANALYSIS block and temperature 0 for deterministic turns so simple prompts skip chain-of-thought. Jev failures fail open and the session continues normally.

An OpenCode plugin that prunes stale tool calls and truncates bulky results on the outgoing V2 request using Jev, leaving stored history untouched and failing open when Jev is unreachable.

OpenCode plugin that replaces LLM compaction summaries with Jev keep/drop judgments: stale tool calls and outputs are pruned while user and assistant text is preserved verbatim, falling back to the built-in summary when Jev cannot help.

dax previews how fast browser use can be with Jev as the decision layer and OpenCode's browser-use CLI, quote-posting a demo video of the loop in action.