Signal Garden

AI 工具AI TOOLS· MODEL-INFRA

claw-compactor

open-compress/claw-compactor

Claw Compactor 是一个能把LLM消耗的令牌压缩50-97%的Python工具包。A 14-stage fusion pipeline that compresses LLM tokens by over 50% with zero inference cost, for developers using Claude Code or similar tools.

根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.

适用平台Platforms
claude-code
已识别的要求Documented requirements
API key · Local runtime
许可LICENSE
MIT

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

能力CAPABILITIES

它能帮你做成什么What it helps you do

  1. 01

    压缩文本和代码,节省token费用

  2. 02

    还原被压缩的原始内容

  3. 03

    识别代码结构来压缩

  4. 04

    自动判断文件类型

  5. 05

    一次性处理整个项目文件夹

  1. 01

    Compress codebases by 50–97% without losing data

  2. 02

    Recover original text using RewindStore markers

  3. 03

    Run the full 14-stage pipeline in under 100ms

  4. 04

    Install and use with a single pip command

上手GET STARTED

怎么装How to install

PIP · Python
pip install claw-compactor

选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.

打开项目文档Open project documentation ↗

使用限制LIMITATIONS

限制与风险Limits and risk

以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

未知Unknown

01需要 API KeyREQUIRES API KEY
是Yes
02需要本地环境NEEDS LOCAL RUNTIME
是Yes
03需要 DockerNEEDS DOCKER
未在文档中发现Not found in the docs
04难度DIFFICULTY
需要本地环境Needs a local runtime
05许可LICENSE
MITMIT
06阶段STAGE
长期未更新Not updated
创建于 10 FEB 2026Created 10 FEB 2026

静态扫描STATIC SCAN

在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.

静态扫描未发现明显风险,但不代表安全。A static scan of the documentation found no known risk patterns, but this does not guarantee the software is safe.

项目动态PROJECT ACTIVITY

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

-0.1%-0.1%

2.0k → 2.0k stars · 49 个快照2.0k → 2.0k stars · 49 snapshots

状态STATUS

长期未更新Not updated

项目发布仅两个月就获得2006颗星,社区关注度高。2006 stars and 1 open issue show active community trust

每周一周刊Monday weekly digest

每周一 1 封:本周热度最高的 10 个 GitHub 新项目。免费,随时退订。One email each Monday: the 10 hottest new GitHub projects this week. Free, unsubscribe any time.

看第 1 期Read issue 1

订阅即表示你同意我们按隐私政策发送每周一周刊。我们会记录这次订阅的来源页面和活动标签,这条记录不包含 IP 地址。Subscribing means you agree that we email the Monday weekly digest as described in the privacy policy. We record the referring page and campaign tag for the signup, and that record does not include an IP address. 隐私政策Privacy Policy

订阅每周一周刊Subscribe to the Monday weekly digest
PROVENANCE · 这些结论的依据是什么Where these conclusions come from
来源 URLSource URL
https://github.com/open-compress/claw-compactor
原始数据哈希Raw data hash
c8764bf266746ab86bb98fa0268d374b
解析时间Parsed at
2026-10-03T11:00:40.559Z
最后一次验证Last verified
2026-11-20T22:14:42.723Z
增长测量时间Growth measured
2026-11-20T23:59:22.010Z
发现查询Discovery queries
focus:token:code:save-tokens, focus:token:code:token-usage, focus:token:repo:cost-tracker
分类来源Category source
rules
焦点Focus
token (16)
完整解析证据 JSONFull parse evidence JSON
{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "SKILL.md: …ttp://localhost:8403 model: claude-code/sonnet max_tokens: 4096 th…"
    }
  ],
  "apiKey": "environment variables export ANTHROPIC_API_KEY=sk-ant-... # Preferred # or export OP",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 5,
      "dev-tools": 3,
      "indie-web": 0,
      "skill-agent": 0,
      "productivity": 1
    },
    "primary": "ai-tools",
    "secondary": "model-infra"
  },
  "localRuntime": "install: pip, git-clone",
  "skillMdTotal": 1,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "1 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "SKILL.md"
  ],
  "skillMdFetched": 1
}