Context compaction with decision models

Claude Code and Codex plugin where Jev judges each turn for model routing, delegation, evidence search and compaction.

Claude Code mod using Jev to pick model and effort per turn, size subagents, and prune stale context verbatim instead of summarising.

Dependency-free CLI and Codex skill that send local state to Jev for typed judgments and return answers without echoing the state.

Claude Code kit wiring Jev into a tool-call guard, sub-agent sizing, file search, a browser agent, review, belay and compaction.

Claude Code mod that hands small decisions (routing, skill choice, screening, gating, trimming) to Jev or another decision backend.

Claude Code (and Codex) plugin that trims long Bash output chunk by chunk with Jev before it reaches the model, without summarising.

Self-hosted MCP research server that filters search results and page blocks with Jev, returning compact evidence with provenance.

Claude Code plugin where Jev asks one yes/no per standing rule and delivers only the rules relevant to each prompt, once per session.

Scores installed Claude Code skills against the current project with Jev and hides irrelevant ones via skillOverrides.

Local Python MCP service that keeps the skill catalog out of the agent's context and lets Jev pick which SKILL.md files to load.

Pre-message hook that keeps or drops SKILL.md files before the first model call, using local overlap or Jev keep/drop judgments.

Claude Code and Codex plugin that removes skills from context and lets Jev decide each turn which SKILL.md bodies to inject.

One-command npx installer for a set of Jev-powered agent tools: context compaction, browser agent, prompt enhancer and skill router.

Jev decision layer for DeepSeek Harness, MCP hosts and plain Node, offline by default with disclosed egress and opt-in gates.

Go CLI that gives coding agents Jev-powered lookups and calibrated yes/no or choice verdicts instead of reading whole files.

Prunes long command output for coding agents by asking Jev which lines matter for the task, keeping original text and order.

Toolkit where Jev condenses large MCP responses for Claude Code and maps Codex requests to reviewed, fixed repository operations.

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.

MCP server that returns only the JS/TS code a task needs by following the TypeScript compiler graph and asking Jev about relevance.

Assembles source-linked evidence for an AI task within a token budget using Jev relevance judgments and diversity-aware selection.

Middleware for LangChain deepagents where Jev ranks and verifies which SKILL.md skills each turn needs, keeping the rest out of the prompt.

Claude Code plugin that compacts by moving old tool results to local files with no summary, with Jev picking which to recall by question.

MCP router that catalogs and deduplicates tools and exposes each agent only a relevant, authorised subset using typed decisions.

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

Jev-powered adversarial or advisory reviewer for the omp coding agent, plus a typesafe_ask tool, plan/stop gates and context compaction.

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

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.

Claude Code plugin with three Jev tools: verbatim context compaction, per-edit model routing and per-prompt skill selection.

Pi extension that prunes stale tool calls with two Jev yes/no questions each, keeping text verbatim and leaving summaries to Pi.