pi-jev-compaction

Where it calls Jev

const response = await fetcher(options.endpoint ?? 'https://api.typesafe.ai/v1/systemone', {

src/client.ts:13

The link points at the commit we read, so the line number still holds.

What it asks Jev

These question sets are lifted from this project's source exactly as written.

import { experimental_evaluate as evaluate } from 'ai';

const { answers } = await evaluate({
  model: 'typesafe-ai/jev',
  state,
  questions: {
    q: { type: 'boolean', instructions: 'Keep this exact call and output?' },
  },
});

Other projects in this category

• yoshi ▶ — Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy
• jevlogs ▶ — Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.
• omp-jev-compaction ▶ — Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter
• opencode-jev-compactor ▶ — Jev powered OpenCode compaction
• codex-context-diet ▶ — Codex plugin: Jev-guided dieting of bulky tool results
• fast-jev-compaction — Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
• invalidate — The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev.
• jev-recall — Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev