Sarup

Name: Sarup
Author: PHUICMT

作者：PHUICMT版本 0.2.0i★ –i在你的电脑上运行

注册名称io.github.PHUICMT/sarup

安装

概览

作者提供的说明（英文原文）

Thai-first context compression; shrinks long Thai and English text, originals retrievable.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
注册中心没有列出需要填写的密钥。

你需要

PyPI已安装 Python 的 uv（用于 uvx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "sarup": {
      "command": "uvx",
      "args": [
        "sarup"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add sarup -- uvx sarup

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "sarup": {
      "command": "uvx",
      "args": [
        "sarup"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "sarup": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "sarup"
      ]
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 PHUICMT 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32599 个服务器的 0%
发布到注册中心的时间比此分类中其他 32599 个服务器的 77% 更新
基础检查结果等于或优于此分类中其他 32599 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Sarup 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.2.0）于10天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Zendesk

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新

安装

Zendesk

作者：pipeworx-io

Zendesk MCP Pack — tickets, users, organizations via OAuth.

电脑或云端今天更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

สรุป · Sarup

Thai-first context compression for Claude Code. An MCP server that actually shrinks Thai (50–78% fewer tokens) and caches every original so nothing is ever lost. Measured for what matters too: whether Claude still answers correctly.

*สรุป* means "to summarize." Headroom routes Thai through noop (0% savings) because its

whitespace tokenizer can't find Thai word boundaries. Sarup uses PyThaiNLP segmentation, so it

compresses Thai as well as English — and caches every original so nothing is ever lost.

Highlights
Why it's safe — the two-tier guarantee
How it works
Tools
Compression modes
Measured results
Example
Install
Register with Claude Code
Auto-compression hook
Privacy & data
Configuration
Project structure
Tech stack & techniques
Testing
Roadmap
License

Highlights

🇹🇭 Real Thai compression — PyThaiNLP newmm word segmentation, not whitespace.
♻️ Lossless by guarantee — every compress caches the original; verified: true proves a byte-for-byte round-trip.
🎚️ Five modes: from offline 1 ms TF-IDF to a 78%-savings cascade.
🧠 Optional local LLM — embeddings + rewrite via Ollama, with automatic offline fallback.
📏 Honest metrics: a real tokenizer (tiktoken) at runtime; Claude's own tokenizer and a Thai QA eval for the published numbers (Does Claude still get it right?).
🕳️ Visible gaps: […] marks every place sentences were dropped, so Claude retrieves instead of mistaking a nearby fact for the answer.
🔌 Content-aware — JSON compaction, log dedup, and verbatim code-fence preservation built in.
🛟 Can't break Claude — it's an MCP tool, not an API proxy; if the server is down the tools just go away and Claude keeps working.

Why it's safe — the two-tier guarantee

Tier	What	Guarantee
Compressed view	the shrunk text the model works on	lossy · small · cheap
Retrieval store	the original, keyed by a stable hash	lossless · recoverable

Aggressive lossy compression is safe *because* the original is always one sarup_retrieve(hash) away. This is how "maximum savings" and "100% accuracy" coexist — they live in different tiers.

How it works

Two entry points feed one engine: a cheap compressed view the model reads, and a lossless retrieval store that can restore the original byte-for-byte.

flowchart TD

M["🧑 Manual sarup_compress()"]:::entry --> R A["⚙️ Automatic PostToolUse hook (Read · Bash · Grep)"]:::entry --> R

R{"Sarup compress extractive · semantic · abstractive · pipeline"}:::engine R -- "compressed view 50–78% fewer tokens" --> V["📄 Model context"]:::lossy R -. "cache original" .-> S[("🗄️ Retrieval store hash → original")]:::lossless

V -. "need full detail?" .-> RET["🔑 sarup_retrieve(hash)"]:::lossless RET --> S S == "byte-for-byte ✓" ==> V

classDef entry fill:#e0e7ff,stroke:#6366f1,color:#111 classDef engine fill:#fde68a,stroke:#d97706,color:#111 classDef lossy fill:#fef3c7,stroke:#f59e0b,color:#111 classDef lossless fill:#bbf7d0,stroke:#16a34a,color:#111

Manual — the model calls sarup_compress / sarup_retrieve itself.
Automatic — the hook intercepts large tool outputs, caches the original to SARUP_DB_PATH, and substitutes the compressed view + a retrieval hash. Source code is skipped; small outputs pass through untouched.

Tools

Tool	Purpose
`sarup_compress(content, target_ratio?, lossless?, query?, mode?)`	Compress; returns compressed text, hash, token metrics,`verified`, `token_method`.
`sarup_retrieve(hash)`	Recover the original content byte-for-byte.
`sarup_stats()`	Cumulative session savings.

`sarup_compress` arguments

Arg	Type	Default	Meaning
`content`	string	—	Text to compress (required).
`target_ratio`	number	`0.5`	Fraction of prose to keep (0.1–0.9).
`lossless`	boolean	`false`	Only apply lossless transforms (whitespace / JSON compact).
`query`	string	`""`	What you need from the text; sentences matching it are kept. Pass it whenever you know: it took the QA eval from 69% to 100% at the same size.
`mode`	string	`extractive`	See modes below.

Compression modes

Mode	How	Needs Ollama	Savings¹	Speed¹	Output
`extractive` (default)	TF-IDF scoring + fact boost + n-gram dedup	no	52.7%	~1 ms	verbatim subset
`semantic`	Embedding centrality + cosine dedup	yes	63.8%	~2 s	verbatim subset
`abstractive`	Local-LLM rewrite	yes	44.4%	~8 s	paraphrased
`pipeline`	Cascade: semantic → abstractive	yes	78.2%	~6 s	paraphrased
`auto`	semantic if Ollama is up, else extractive	optional	63.8%	~2 s	subset

¹ Measured on a 10-sentence Thai paragraph (522 tokens), rewrite model gemma4:12b. Every mode stays 100% recoverable via the store; Ollama modes degrade gracefully to extractive when the backend is down. (gemma4:e4b: pipeline 82.2%; June 2026, gemma3:12b: 88.1%.)

Extractive and semantic output is a verbatim subset of the input sentences, with […] on its own line wherever sentences were dropped. Sentences carrying specifics (numbers, Thai digits, identifiers like X-Api-Key) score higher than general statements, since those are what questions ask about.

Measured results

$ .\.venv\Scripts\python.exe bench\benchmark.py

sample before after savings verify Thai prose 522 247 52.7% OK Thai prose (aggressive) 522 189 63.8% OK English prose 105 60 42.9% OK JSON (lossless) 67 44 34.3% OK Logs 563 300 46.7% OK TOTAL 1779 840 52.8% ALL OK → 100% recoverable

Mode comparison (Thai prose, 522 tok): extractive 52.7% (1ms) · semantic 63.8% (2.1s) · auto 63.8% (2.1s) abstractive 44.4% (8.3s) · pipeline 78.2% (5.8s) ← gemma4:12b

Token counts via tiktoken cl100k_base. That is OpenAI's tokenizer and undercounts Claude, most of all on Thai; bench\benchmark.py --claude adds a column from Claude's own tokenizer (Anthropic count_tokens, needs an API key).

Does Claude still get it right?

Fewer tokens only help if the facts survive. bench\eval_qa.py compresses 8 Thai documents (incident report, meeting notes, API docs, HR policy, product spec, support chat, README, sales report; half line-per-sentence, half dense paragraphs) and asks Claude Opus 5.5 32 questions from the compressed view alone, graded deterministically:

$ .\.venv\Scripts\python.exe bench\eval_qa.py        # uses your local `claude` login

mode claude tok saved correct abstain wrong ────────────────────────────────────────────────────────────── original 4601 0.0% 100% 0% 0 extractive:0.5 3204 30.4% 69% 31% 0 extractive:0.3 1969 57.2% 44% 56% 0 semantic:0.5 3214 30.1% 62% 38% 0 extractive:0.5+q 3207 30.3% 100% 0% 0 abstractive:0.5 2697 41.6% 91% 9% 0 ← gemma4:12b pipeline:0.5 1854 59.8% 59% 41% 0 ← gemma4:12b

(gemma4:e4b scored the same: abstractive 91%, pipeline 59%, wrong 0.)

wrong = 0 is the safety property: when a fact was dropped, Claude said so (*abstain*) and in real use would call sarup_retrieve. It did not guess from what was left.
abstain is the real cost of blind compression: about a third of specific questions need a retrieval round-trip at 0.5. Know what you're looking for? Pass it as query (+q row).
abstractive keeps the most facts per token (91% at 42% saved) because a rewrite can keep every number while dropping words; extraction can only drop whole sentences. It costs seconds per document, so use it through sarup_compress, not the hook.
In both evals no paraphrase changed a fact into a wrong one, but 8 documents can't prove a rewrite never will, which is why the original stays one sarup_retrieve away.
Token counts here are Claude's own (from the answer calls' usage) and include the ~40-token [sarup: …] footer, which weighs heavily on these short (~570-token) documents and fades on the large outputs the hook actually compresses.
8 documents is a small sample; differences of a couple of questions between modes are noise.

Before the fixes this eval drove (Oct 2026): dense Thai paragraphs were not compressed at all (the sentence splitter's model wasn't installed), extractive:0.5 answered 59% with one confident wrong answer, and semantic:0.5 47%.

Example

A real sarup_compress call on a Thai paragraph (mode="auto", Ollama up → semantic):

// → sarup_compress(content="…518-token Thai paragraph…", mode="auto")

{ "compressed": "จุดเด่นที่สำคัญที่สุดคือมันไม่มีทางทำให้ Claude พัง…", "hash": "caa568140bec0ff734937cf5", "original_tokens": 518, "compressed_tokens": 154, "tokens_saved": 364, "savings_percent": 70.3, "transforms": ["semantic

只显示了开头部分；其余内容请在仓库中阅读