PRODUCTIVITY/效率应用·NOTES-DOCS

claude-code-memory-setup

lucasrosati/claude-code-memory-setup

Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify.

打开仓库Open repository

怎么装：Install: pip install claude-conversation-extractor

02 / 现在的位置02 / Why now

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

+0.3%+0.3%

1.0k → 1.0k stars · 4 个快照1.0k → 1.0k stars · 4 snapshots

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

PIP

$

Python 用户的完整版安装，包含命令行工具。The full install for Python users, including the command-line tool.

PIP

$

Python 用户的完整版安装，包含命令行工具。The full install for Python users, including the command-line tool.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。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

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要 API KeyNeeds an API key

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/lucasrosati/claude-code-memory-setup
原始数据哈希Raw data hash: 746334a2876f968c372f653bb9bb4766
解析时间Parsed at: 2026-10-06T23:30:13.413Z
最后一次验证Last verified: 2026-10-06T22:09:57.556Z
增长测量时间Growth measured: —
发现查询Discovery queries: focus:token:repo:topic-token-optimization
分类来源Category source: rules
焦点Focus: token (8)

静态扫描STATIC SCAN

01下载未知二进制Downloads an unknown binaryreadme
```
chmod +x ~/scripts/sync_claude_obsidian.sh
```

02需要系统权限Needs system permissionsreadme

Grant Full Disk Access to your terminal in System Preferences → Privacy & Security.

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …# Claude Code + Obsidian + Graphify: The De…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …upported (`cursor`, `codex`, `opencode`, etc.). **1.5. Set up API k…"
    }
  ],
  "apiKey": "fore running: ```bash export ANTHROPIC_API_KEY=\"your-key-here\" # or export MOONSHOT_AP",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 3,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 3,
      "productivity": 6
    },
    "primary": "productivity",
    "secondary": "notes-docs"
  },
  "localRuntime": null,
  "skillMdTotal": 0,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 4,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 0,
    "security": 0,
    "marketing": 0,
    "productivity": 6
  },
  "classification": [
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme"
  ],
  "skillMdFetched": 0
}