Lossless AI Memory with Longhand for Claude Code

说明与用途

Longhand 是一个针对 Claude Code 会话的本地无损记忆解决方案。它通过将 JSONL 日志索引到 SQLite 和 ChromaDB 中，取代了 AI 摘要，提供了快速的语义搜索、隐私保护和离线功能。

问题

AI memory tools typically summarize sessions, resulting in lossy data where specific debugging steps, reasoning traces, and failed attempts are discarded. Additionally, relying on vendor context windows creates privacy risks, vendor lock-in, and dependency on network connectivity.

结果

Longhand provides a lossless, offline, and private alternative to AI memory summarization. It indexes Claude Code's JSONL logs into local SQLite and ChromaDB stores, enabling fast semantic recall (~126ms) without API calls or data loss. It supports forensic replay of code states and is portable across models.

工作流

• Install Longhand via pip: pip install longhand
• Run setup to backfill existing Claude Code history and install auto-ingest hooks: longhand setup
• Longhand automatically captures new sessions via a SessionEnd hook in Claude Code.
• Query history using the MCP server tools, e.g., longhand recall "that webhook fix from last week"
• Use specific tools like replay_file to reconstruct file states or get_session_timeline for chronological replays.

证据

Semantic recall across 100+ sessions: ~126ms

来源

Storage footprint: ~1GB for a heavy power user, 200–400MB typical

来源

API calls per query: zero

来源