jevbooks

← All projects

pi-jev-context

Nyarlathoteppppp/pi-jev-context

Pi extension: dedupe reads, sieve logs, recall originals.

Scoring & Ranking0.35Runner-up: Data Labeling & CurationFail open, fail closed
Automated README summary

Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Pi extension that shortens long tool output before it enters context, keeping cached prompt prefixes intact. It offers read dedupe, a Jev log sieve, and a recall tool. For Pi users who want token savings without losing information.

How it uses Jev

In the sieve layer (opt-in), Jev receives the command, recent messages, and the log split into blocks. It returns a probability that the current request needs each block. Blocks with P(needed) below a threshold are hidden, but code guarantees failures, warnings, stack traces, summaries, and request terms survive.

Primitives:score

Technique worth stealing

Use Jev to score blocks of tool output for necessity, then hide only low-probability blocks while preserving critical lines via code.

Try it

pi install git:github.com/Nyarlathoteppppp/pi-jev-context, then /reload. For sieve: set TYPESAFE_API_KEY and /context sieve on.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.23
  • Shows a System One patternFound in material0.78
  • Describes handling uncertaintynot found in the excerpt0.34
  • Reports measured numbersnot found in the excerpt0.10
  • Is a runnable toolFound in material0.96
  • Top-10 learning shortlist signalunclear0.54
  • Is a replica of the modelnot found in the excerpt0.04
  • Solves a common problem (0–2)score on a 0–2 scale1.16 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.23Shows a System One pattern0.78Describes handling uncertainty0.34Reports measured numbers0.10Is a runnable tool0.96Top-10 learning shortlist signal0.54Is a replica of the model0.0400.51Solves a common problem (0–2)1.16 / 2012

no-judgment band (0.40–0.60)

Design patterns
Fail open, fail closed0.92Funnel0.57Viewfinder0.33Flight recorder0.33Menu0.2900.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 13 Oct 2026.