Skip to content

Pi Jev Context — kevinpita

Pi extension that uses Jev to judge which older session messages are still worth sending to the model, hiding low scorers from future requests while leaving the session transcript itself intact.

Stars
2
Language
TypeScript
License
MIT
Published by
Community
Author
kevinpita
Last verified
Oct 2026

This is one of several Jev listings for the same project. The canonical entry is Pi Jev Context — Nyarlathoteppppp.

About this project

Jev Context for Pi Keep useful context. Hide old noise. Keep your original history. A Pi extension that uses TypeSafe Jev to judge which older messages are still useful. Low-scoring content is hidden from future model requests, not deleted from your session. Opt-in · Reversible filtering · Branch-aware cache · No extra runtime dependencies. Requires Pi 0.85.1+, Node.js 22.19+, and a TypeSafe API key. TypeSafe usage can incur charges. Jev is a separate judgment service, not your main coding model.

Quoted from the project's README. Read the full README.

Highlights

  • The default threshold of 0.8 is aggressive by design — 0.81 stays, 0.80 is hidden — and /jev threshold re-filters from cached scores.
  • User requirements, system instructions, todo operations, images, incomplete tool exchanges and the latest five tool pairs are never judged.
  • Judging is off by default and reversible: /jev off restores unfiltered history and /rejev rejudges the active branch while idle.
  • Judgments and settings persist with the session branch, and with the cache on only new or changed candidates are sent.

Watch out

When enabled, candidate assistant history, tool arguments, text results and recent conversation excerpts go to TypeSafe's System One endpoint and can contain private code or secrets; nothing is sent while it is disabled. On an API error judging pauses but previously saved pruning still applies, so a failed scan does not hand your context back — you need /jev off. Cached scores do not adapt when the topic changes. Filtering can invalidate your model provider's prompt cache, and Jev cannot recover messages Pi's own compaction already removed. The README's screenshots are illustrated previews, not live captures or benchmark results. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

20GitHub stars
TypeScript SDK and CLI coding agent where Jev only picks options while your code runs effects, building programs as syntax trees.
Jev Agents & MCP#community#awesomejev#catalog-import
22GitHub stars
Runnable agent harness that moves pick, score and yes-no loop choices to Jev or Laya in milliseconds while reserving the language model for writing, compiling DECISION.md into executable questions.
Jev Agents & MCP#community#jevbest#catalog-import
35GitHub stars
Diff-aware test selector that sends the git diff to Jev with one question per test, then prints the native filter flags and hands them to vitest, jest, node, bun, Playwright, cargo, or go test.
Jev Agents & MCP#community#jevbest#catalog-import
13GitHub stars
Pi extension that classifies each task with Jev over OpenRouter and routes it to a Pareto-optimal model balancing measured quality, cost, and latency under a role policy.
Jev Agents & MCP#community#jevbest#catalog-import
15GitHub stars
Node CLI that lints a file tree against fuzzy natural-language rules in one Markdown file, judging each matched file with a swappable TypeSafe-backed judge.
Jev Agents & MCP#community#jevbest#catalog-import
106GitHub stars
Decision layer exposing Jev's typed yes-no, choice, and score answers to DeepSeek Harness and MCP hosts, offline by default with every network transmission disclosed per feature.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai