All decision model projects

Minimal Pi extension and TypeScript client registering a jev_evaluate tool for noul, choice and score across five Jev platforms.

Lean Pi supervisor: zero-token regex guardrails, done-check verification, per-turn routing and a Jev/Clef semantic slop gate on diffs.

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

Pi extension that checks proposed code edits against repository Markdown rules with Jev, reporting rule text and line ranges.

Pi extension asking Jev four questions per prompt (task kind, complexity, capability, deep reasoning) to pick a budget-aware model tier.

Pi /jev slash command: Jev picks model tier and thinking level for one prompt in about 200 ms before sending it.

Read-only Odoo support package for Pi: Jev selects bounded business routes and entities, Python enforces scope and verifies answers.

Pi extension where Jev decides whether a reply needs rewriting, then your model clarifies it and may add a small visual.

Pi model router using Jev via Vercel AI Gateway to pick a model and reasoning effort once per session, then stay pinned.

Pi router that classifies each task with Jev via OpenRouter and picks a model from the quality-cost-latency Pareto frontier.

Jev Sentinel: guard for Pi, Claude Code and Codex that checks tool calls, tool outputs and replies, failing closed.

Pi extension that removes the skill catalogue from the system prompt and adds a skill_search tool where Jev rates each skill 0-2.

Pi extension that strips the inlined skill list and asks Jev which single skill, if any, to load per turn.

Pi/omp extension that keeps the model fixed and has Jev choose only the thinking effort each turn via a local SPI daemon.

Pi extension that audits whether the rpiv-todo board matches visible work and nudges the agent when it drifts off-task.

Pi codemode tool that classifies whole project files with caller-defined Jev questions, returning paths and typed answers, not source.

Pi extension for four-tier model routing with an optional classifier advisor (formerly Jev/Clef-specific, now any Pi classifier).

Pi observational memory where Jev answers keep/kind questions on history chunks, building a verbatim ledger and topic files.

Rule-engine layer for Pi where Jev answers closed questions (destructive? leaked key? done verified?) with packs and fail-open actions.

Pi package that gates pi-subagents dispatches with one Jev call against configurable rule sets and adds a jev_ask tool.

Adaptive thinking-level router for Pi: Jev or local rules pick low/medium/high/xhigh at task start, on reasoning failures and when stable.

Advisory Jev sidecar for Pi: four pre-flight hazard checks before bash/write/edit and four diff-quality checks after edits.

Pi extension that auto-approves routine Bash commands via a System One model and escalates flagged ones, including obfuscated, to a human.

Pi extension exposing Jev as five narrow tools (noul, choice, score, evaluate, pinned ask) while code keeps thresholds and actions.

Pi extension that classifies each request with Jev and routes it to one of three configured models, with doctor checks and shadow mode.

Minimal Pi permission gate: deterministic rules first, then a classifier answers allow, ask or deny per gray-zone tool call; fails closed.

Pi guardrails on pi-typesafe that steer the agent: Jev checks rule breaks, irreversible actions, stuck loops and unverified done claims.

KDE Plasma 6 assistant widget for many LLM providers, with a Decisions adapter that answers each message with a Jev verdict and confidence.

Node CLI for goal-driven E2E tests: Jev picks the next step from a code-generated action space, playwright-cli executes, code asserts.

Chrome extension that covers YouTube comments while one Jev yes/no per comment checks for spoilers of the video or protected titles.