本文へスキップ
TakoAPI
スキル一覧に戻る

chaos-mind

hargabyte 作

Notes & PKM
1.6kダウンロード数はclawskills.shが公開している値です
2スター
0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

Hybrid search memory system for AI agents.

説明

このスキルでできること

CHAOS Memory is a hybrid search memory system for AI agents that combines BM25 keyword matching, vector semantic similarity, graph relationship bonuses, and access-pattern heat signals into a single retrieval layer. Memories are stored and searched manually via a CLI. Auto-capture from session transcripts exists but is disabled by default.

Combining four retrieval signals in one query surfaces more contextually relevant memories than keyword or semantic search alone.

使いどころ

  • Searching past architectural decisions before starting a new task
  • Storing a pricing or product decision mid-session for future retrieval
  • Looking up environment configuration details across agent sessions
  • Anchoring a technical decision to specific code file locations via Cortex
  • Scanning recent memories before a code review or handoff

ワークフロー例

入力

User asks: find any past decisions about authentication, then record today's choice

エージェント
  1. 1

    Run chaos-cli search "authentication" --mode index --limit 10 for a fast token-efficient scan

  2. 2

    Review returned memory summaries for relevant prior decisions

  3. 3

    Run chaos-cli search "authentication" --mode full --limit 3 on the top hits for full detail

  4. 4

    Store the new decision: chaos-cli store "Switched to JWT for stateless sessions" --category decision --priority 0.9

  5. 5

    Confirm storage with chaos-cli list 5

出力

Agent surfaces prior auth decisions and persists the new one with high priority for future retrieval.

要件

  • Ollama installed locally (only required if enabling the opt-in auto-capture feature, available at ollama.com)

インストール

clawhub install hargabyte/chaos-mind

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