pi-jev-context-curator

A Jev based context curator for pi

How it uses Jev

A pi extension that curates the context sent to the LLM before each call — using TypeSafe AI's Jev model to decide which context is actually needed.

Highlights

  • Groups messages into units — an assistant tool-call message plus its tool results stay together as one atomic unit, so curation never orphans a tool result.
  • Checks each unit against the judgment checkpoint : every unit Jev has already judged is recorded by content fingerprint, so past decisions are reused and the same data is never se…
  • Sends only the new units (those after the checkpoint) to Jev's /v1/systemone endpoint. One primary yes/no ( noul ) question decides keep/remove, alongside two native choice questi…
  • Units Jev rejects are omitted from the current model context and that decision is re-applied on subsequent context events (pi itself only lets extensions transform the per-call pa…
  • Every newly removed unit is also written as a durable, session-scoped pi entry. It appears as a collapsed [jev removed] record and can be expanded to inspect the removed text. The…

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to pi-jev-context-curator

Browse all
dsh-context-curator project preview
Agent tooling
DSH-native context compaction that keeps text verbatim: scores every tool call and result with Jev, drops only the stale ones, and falls back to DSH native summary when unsure.
pi-fast-jev-compaction project preview
Pi extension: verbatim context compaction with TypeSafe Jev decisions
pi-jev-router (philippdubach) project preview
A minimal Pareto-optimal OpenRouter model router for pi, based on Jev
tinystruct-typesafe-sdk project preview
A tinystruct-based TypeSafe SDK with JEV model.
jev-document-classification project preview
JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.
typesafe-showcase project preview
Demos & playgrounds
Next.js UI showing off TypeSafe's System One model (Jev) — parallel Noul judgments and a Choice-based citation checker, deployable to Vercel
jev-playwright-mcp project preview
Browser & computer use
Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.
jev-web-analyzer project preview
Benchmarks & research
See what Jev thinks about your SaaS website — powered by ReplyNodes web context and Vercel AI Gateway.
heyreach-jev-bot project preview
Applications
Signal-based LinkedIn outbound scoring for HeyReach, running on Jev (TypeSafe System One).