本文へスキップ
TakoAPI
スキル一覧に戻る
—まだ評価がありません
あなたの評価

概要

Local RAG system for agent memory using ChromaDB and sentence-transformers.

説明

このスキルでできること

Local RAG system that gives AI agents persistent memory across sessions. Uses ChromaDB for vector storage and sentence-transformers for local embeddings. Indexes session logs, daily notes, and markdown files for semantic search.

Runs entirely on local hardware with no external API calls, so memory stays private and works offline.

使いどころ

  • Searching past conversations before answering a question
  • Indexing daily notes so decisions persist across restarts
  • Resuming context after an agent session ends and restarts
  • Building a searchable log from agent session history
  • Scheduling automatic memory updates every few hours via cron

ワークフロー例

入力

User asks: 'What did we decide about the API design last week?'

エージェント
  1. 1

    Run recall 'API design decisions' --json to query ChromaDB

  2. 2

    Retrieve top matching chunks from indexed session digests

  3. 3

    Include relevant context in the response to the user

出力

Agent responds with relevant past decisions pulled from indexed memory files

インストール

clawhub install ttboy/ouyang

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク