HunterAlphaHub
OpenRouter model reference Facts from the public catalogue, dated and labelled
Jev Laya Fable 5.2 Verified
2026-11-13

GitHub · Coding and context

tamaratran/fast-jev-compaction

The honest version of shrink-the-context: deletion instead of paraphrase.

The repository's GitHub card, read on 2026-09-23

What it does

A Claude Code plugin, also usable as an npm library, that replaces the usual LLM summarisation of a long session with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, and everything kept stays verbatim.

The repository's own description: “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.”

How it works

It never rewrites what it keeps — the README's sentence is "This library never rewrites anything. It only deletes tool calls and tool results" — which is the opposite of a lossy summary: a file path or an exact error cannot be paraphrased away if it is never paraphrased.

The repository, by the numbers

Stars
6,978
Forks
429
Language
TypeScript
Last push
2026-09-18

Read from the GitHub API on 2026-09-27. Stars and the last push move daily — quote them with the date, the way we do.

What we checked

  • the tree: hooks, src, tests, types, examples, .claude-plugin
  • package.json plus tsconfig files — an npm package with a test directory
  • MIT LICENSE
  • README states the delete/truncate-only rule and the reason (summaries lose exact details)

What we did not check. We did not install the plugin into a session, so how much context it actually saves is unmeasured here.

Open the repository ↗All builds

Send us a link

A project built with Jev, a post, a video, a correction, a tip. We open the link, check it says what you said it says, and write the entry ourselves.

Required a link, and an email to reply to. Optional everything else.

Add context — all optional

One or two sentences about what it does, in your words. We write the entry ourselves.

Cost, latency, a benchmark — anything you measured. We attribute these to you.

We store what you type and email it to ourselves. No IP address, no user agent, no referrer — the same rule as the mailing list.

What happens to what you send →