fast-jev-compaction
Project / 项目 · In the catalogue / 在目录中查看
What Jev decides here · Jev 在这里做什么决定
noul: read in the code by a person 由人在代码里读到
a person read the call site 有人读过调用点 · · Cited file / 引用的文件: src/request.ts
Summary · 摘要
A Claude Code plugin that replaces the compaction summary with per-item decisions: stale tool calls are dropped or truncated, everything kept stays verbatim.
一个 Claude Code 插件，用逐条决策取代压缩式摘要：过期的工具调用被丢弃或截断，保留下来的全部逐字不变。
Notes · 备注
Exactly two nouls per tool call: does knowing this call happened still matter, and is the full output still needed verbatim. Despite the word "scored" in its own description, no score primitive is used.
每次工具调用恰好两个 noul：知道这次调用发生过是否还有意义、以及是否还需要完整原文输出。尽管它自己的描述里用了「打分」，实际并未使用 score 原语。
Launches · 发布记录
Not launched yet. 还没有发布过。 Launch it / 发布它 ↗ · How a product launches / 怎样发布一个产品
Makers · Maker
Made this? Confirm or correct its entry / 这是你做的？确认或更正条目 ↗
The same form takes the product's one line and a demo link, in its maker's own words. 同一个表单也可以补上产品的一句话和演示链接，用 Maker 自己的话。
Badge for its README · README 徽章
[](https://kydlikebtc.github.io/awesome-jev/products/fast-jev-compaction.html)One line for the product's README, linked to this page. The picture says that it is listed; while it is on the launch board, that it is launching; after a week in the top three, its place. It is rebuilt with the site, so the line never needs changing. 放进产品 README 的一行，链接到本页。图片显示已收录；在发布榜上时显示正在发布；进过某周前三后显示名次。它随网站一起重建，这一行不用再改。
Also under this pattern · 同一模式的其他产品
jcode: memory recall without embeddings
Replaces the whole retrieval stack for memory recall — no embeddings, no BM25, no reranker — with one batched Noul per candidate memory.
jevgrep (dzhng)
CLI and agent skill that finds code by asking what it does: `jg "How are telemetry events recorded?" ./repo` has Jev judge relevance across folders, files and declarations and returns files and verbatim excerpts. The author reports the same 8 of 10 SWE-bench tasks solved at ~30% lower cost.
hermes-jev-skills
Nine agent skills plus a CLI covering model routing, memory filtering, turn retention, one-of-many skill selection and next-action choice.
mu
Coding agent and desktop app built on pi that asks Jev at 40 decision points which tool-output chunks enter the context, which stale tool results to drop, whether a rule-flagged command was asked for and whether fetched pages or MCP output carry injected instructions.
compact-adviser
Plugin answering one question, should I /compact now: one Jev request asks two choices (is the latest unit of work finished; hands-on or coordination), combined in code into a score whose floor relaxes from 0.90 to 0.50 as the context fills. It hints, or compacts on Pi and Claude Code if you opt in.