本文へスキップ
TakoAPI
スキル一覧に戻る

human-like-memory

jianghaibobo2015-rgb 作

Coding Agents & IDEs
—まだ評価がありません
あなたの評価

概要

This skill provides long-term memory capabilities for conversations.

説明

このスキルでできること

Adds persistent memory to AI conversations by saving and recalling context across sessions. The agent proactively searches memory when past context is relevant and automatically saves decisions, preferences, and facts. Memory is stored and retrieved via the human-like.me API.

Default AI sessions are stateless, so this skill fills that gap by automatically persisting and retrieving context without requiring the user to repeat themselves.

使いどころ

  • Resuming a project after days away without re-explaining context
  • Tracking coding style and tool preferences across sessions
  • Recalling why a technical decision was made weeks earlier
  • Continuing a multi-session debugging investigation
  • Remembering project names, deadlines, and team details

ワークフロー例

入力

User asks: "Do you remember what database we chose for the project?"

エージェント
  1. 1

    Identifies the subject as 'database project decision' and strips action words from the query

  2. 2

    Runs: node memory.mjs recall "database project decision"

  3. 3

    Receives stored memory entry with the prior choice and rationale

  4. 4

    Incorporates the result naturally into the response without referencing the memory system

出力

"Yes, we decided to use PostgreSQL for the project because of its strong JSON support and reliability."

要件

  • HUMAN_LIKE_MEM_API_KEY environment variable (obtain from human-like.me)

インストール

clawhub install jianghaibobo2015-rgb/human-like-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