OpenCode + decision models

Small stdio MCP server with ask, rank and verify tools backed by Jev, a local event log and installers for several agent harnesses.

CLI that grades the coding-agent sessions on your disk (Claude Code, Codex, opencode, Gemini CLI) with Jev for cents.

Coding-agent plugin that has Jev auto-approve shell permission requests it judges harmless and abstains on anything uncertain.

Accessibility-first macOS computer-use MCP server and CLI, with optional Jev guards on targets and inputs before irreversible actions.

Local-first meeting transcription and conversation memory app whose live voice path runs its evaluations through Jev.

Local code search for coding agents: ripgrep/BM25 shortlist, then Jev judges each chunk's relevance, served over MCP.

OpenCode plugin adding an Auto (Jev) virtual model that routes each turn to one of your configured real models.

OpenCode port of fast-jev-compaction that prunes stale tool calls from outgoing requests verbatim, by default only on compaction.

OpenCode plugin that compacts sessions by Jev keep/drop judgments per tool call instead of LLM summaries, falling back if unhelpful.

OpenCode 2 plugin that asks Jev six questions about every shell command (local or remote via FarHand) and prompts unless clearly safe.

OpenCode orchestrator that keeps a cheap sticky parent model and escalates to strong child subagents only when Jev flags a hard turn.

OpenCode plugin and proxy where Jev picks reasoning effort per step; superseded by reasoning-router.

opencode plugin that routes the agent's small multiple-answer decisions to Jev and labels each answer auto or escalate by confidence.

Decision governor for Pi routing plan strategy, model tier, tool permissions and outcome (finish, retry, replan) through Jev.

Pre-execution hook for coding agents that lets shell commands run, asks a human, or blocks them, with optional Jev classification.

Host-agnostic routing layer that picks model, effort and provider per round for coding harnesses from trajectory evidence.

MCP server exposing Jev as a single evaluate tool for Claude Code, Codex, OpenCode, Antigravity or Cursor.

Local MCP server that adds a jev_decide tool to OpenCode agents, with a conservative confidence-gated policy for a developer agent.

Desktop app running coding agents in parallel git worktrees, with optional Jev judgments of each changed file against the task.

Agent skill that makes a coding agent try Jev first for bounded judgments like classify, rank or gate, and log each attempt.

CLI that filters coding-agent subscriptions by quota and policy, then asks TypeSafe to rank the rest and pick a reasoning effort.

Semantic ArkUI linter for coding agents: a fact extractor finds candidate state bugs and a System One model judges each one.

Experimental Paseo plugin where Jev, local Laya or OpenAI Decisions classifies each message and routes it to a provider/model preset.

Cost-, cache- and quota-aware LLM router that classifies each turn with a Jev-class model, prices every route, and checks cheap answers.

Self-hosted memory MCP server on Cloudflare Workers where a Jev layer judges memory type, salience and durability and re-ranks recall.

OpenCode V2 port of fast-jev-compaction that asks Jev or a local Jev-style model which old tool outputs still matter.

Experimental plugin wiring Jev into coding-agent harnesses to pick skills, tools, models and browser moves, starting with OpenCode.

Agent skill and CLI that chains Jev question design: find decision calls, check fit, draft, lint, calibrate thresholds and plan a cascade.

Local-first, outcome-aware model router for coding harnesses that picks a capability tier per task with Jev and learns from history.

Mac desktop pet agent that does tasks across files, apps and websites, using Jev alone for file chores and an LLM for open-ended work.