name: chat-memory-archiver description: "Extract decisions, todos, knowledge, preferences, and risks from AI chat sessions into structured memory"

Session Archiver

Parse AI chat session logs and extract structured knowledge: decisions made, pending todos, learned facts, user preferences, and flagged risks. Merge across sessions and export to Markdown, JSON, Obsidian, or Notion.

Workflow

1. Parse conversation — Read session log, extract question-answer pairs, tool calls, and decision points.
2. Segment by phase — Label each segment as problem / exploration / decision / action.
3. Extract 5 categories:
4. 📌 Decisions — Choices made, with rationale and alternatives considered.
5. ✅ Todos — Action items, owners, and deadlines.
6. 📚 Knowledge — Facts, code snippets, links, and explanations.
7. ⭐ Preferences — User style, terminology, tools, conventions.
8. ⚠️ Risks — Security concerns, known issues, caveats.
9. De-duplicate & merge — Fuse repeated information across multiple sessions, keep latest version.
10. Topic tagging — Auto-tag each session with relevant domain labels (e.g. #python, #api-design, #deployment).

    来源于7w4.net。

11. Cross-session graph — Build lightweight association graph showing which sessions share topics or reference each other.
12. Format export — Generate output in Markdown, JSON, Obsidian-flavored wiki links, or Notion JSON.
13. Summary — Produce a concise 5-sentence summary of each session for quick scanning.

Sample Prompts

• session-archiver extract --sessions session-2026-06-01.log session-2026-06-02.log
• session-archiver extract --sessions . --format obsidian --outdir ./vault
• session-archiver merge --sessions . --dedup --out summary.json
• session-archiver report --sessions . --graph > session-graph.dot

Safety

• Session logs are parsed locally; never sent to external services.
• Sensitive content (passwords, keys) in logs is flagged during extraction; user must explicitly confirm before inclusion in output.

整体质量中等偏下。功能覆盖全面，文档清晰，但存在严重安全隐患——它承诺会询问用户确认后再导出敏感内容，实际却没有这样做，可能会在不知情的情况下导出包含密码、密钥等敏感信息的日志。另外，它对聊天内容的理解和分类比较简单，可能遗漏或误判重要信息。改进后会更实用。