Cost and rate control with decision models

Rust CLI for Jev that lints typed question sets offline, then sends them and prints probabilities, labels and scores as JSON.

Local OpenAI/Anthropic-compatible proxy where one Jev call picks the model route and thinking level for each coding-agent turn.

Agent skill that has Jev pick the few relevant lines from big logs before your coding agent reads them, with a reversible reduce and ledger.

Offline TypeScript token counter and request-cost estimator for Jev 1.13, a port of the reconstructed jevtok encoder.

Transparent proxy that asks Jev to classify each coding-agent prompt and injects the decision into the agent's context before it generates.

Browser tool that finds bounded decisions in LLM prompts and proposes Jev Choice, Score and Noul questions with SDK code.

Records the full distribution of every Jev answer by state, question and model, so thresholds can move over history with no new calls.

OpenAI-compatible chat cache proxy that asks Jev or a local System One model whether a new question has the same intent as a cached one.

Task plugin for the new-api LLM gateway that adds a native /v1/systemone endpoint for Jev with auth, routing and token billing.

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

Oh My Pi extension that truncates tool calls and results Jev scores as no longer needed, while keeping all user and assistant text verbatim.

Oh My Pi extension where Jev classifies each prompt as simple or advanced and switches the model role, defaulting to advanced on doubt.

OpenClaw context engine that asks Jev which tool calls and results are still needed and drops the rest verbatim, never summarising.

OpenClaw plugin where Jev decides whether a group-chat bot should reply and, optionally, which model tier should answer.

OpenClaw plugin and CLI that turn a plain-language condition into a scheduled trigger, waking the model only when Jev says it is true.

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OpenCode plugin and proxy where Jev picks reasoning effort per step; superseded by reasoning-router.

Pi port of fast-jev-compaction using Pi's context hook, with a savings gate against low-value pruning and retained status notes.

Pi extension routing plan and implementation phases to light, standard or heavy model tiers based on a Jev capability score.

Automatic Pi context clearing: drops superseded tool outputs for free and asks Jev about large older ones, with originals retrievable.

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

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.

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

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

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

Claude Code plugin where a local Decider model on your Mac picks the model and effort level for each subagent task.