本文へスキップ
TakoAPI
スキル一覧に戻る

enhanced-memory

jameseball 作

Search & Research
683ダウンロード数はclawskills.shが公開している値です
1閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Enhanced memory search with hybrid vector+keyword scoring, temporal routing, filepath scoring, adaptive weighting.

説明

このスキルでできること

A drop-in replacement for OpenClaw's default memory search. Uses a 4-signal fusion pipeline combining vector similarity, keyword matching, header matching, and filepath scoring to retrieve memory chunks. Also includes salience scoring and a knowledge graph cross-reference builder.

Achieves 0.782 MRR versus approximately 0.45 for baseline vector-only search by fusing four signals and applying adaptive weighting when keyword overlap is low.

使いどころ

  • Finding relevant past context when vector-only search returns weak results
  • Surfacing stale memory files during agent heartbeat cycles
  • Building cross-reference links between related memory chunks
  • Querying memories with date references like 'last Monday' or 'Feb 8'
  • Indexing updated memory files after significant workspace changes

ワークフロー例

入力

User asks: 'What did I decide about the auth system last week?'

エージェント
  1. 1

    Detects temporal reference 'last week' and applies 3x boost to date-matching files

  2. 2

    Embeds the query using nomic-embed-text via Ollama

  3. 3

    Scores all memory chunks across vector similarity, keyword overlap, header match, and filepath

  4. 4

    Checks if top score exceeds PRF threshold; if not, expands query terms and re-scores

  5. 5

    Returns ranked results with path, score, and snippet

出力

Ranked memory chunks referencing auth system decisions from the relevant timeframe

要件

  • Ollama installed and running locally on port 11434
  • nomic-embed-text model pulled via Ollama

インストール

clawhub install jameseball/enhanced-memory

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