跳到正文
TakoAPI
返回技能列表

tiered-memory

由 bowen31337 提供

Coding Agents & IDEs
1.3k下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

EvoClaw Tiered Memory Architecture v2.2.0 - LLM-powered three-tier memory system with automatic daily note.

描述

该技能的功能

Three-tier memory system (hot/warm/cold) for persistent agent memory across conversations. Facts are distilled, scored with recency decay, and organized in a hierarchical tree index. Critical state syncs to Turso after each conversation for cloud-first recovery and multi-device continuity.

LLM-powered tree search achieves 98%+ retrieval accuracy versus 70-80% for vector embeddings, and context size stays constant at 8-15KB regardless of how long the agent has been running.

何时使用

  • Retrieving an architectural decision made three weeks ago without scanning full history
  • Automatically ingesting daily markdown notes into the tiered memory system
  • Finding all stored URLs associated with a specific tool or project
  • Keeping agent context under 15KB after years of accumulated conversations
  • Restoring full agent memory to a new device in under two minutes

示例工作流

输入

User asks: What did we decide about the BSC integration approach?

智能体
  1. 1

    Agent sends the query to the tree search module

  2. 2

    LLM reasons over the tree index and identifies relevant categories such as projects/evoclaw/bsc and active_context/events

  3. 3

    Warm memory entries from those categories are fetched and ranked by score

  4. 4

    Cold storage is queried for lower-scored archived facts in the same paths

  5. 5

    Top results are injected into the agent context before the response is generated

输出

Fact returned: 'Decided to use raw JSON-RPC for BSC to avoid go-ethereum dependency' with category path, importance score, and any preserved URLs or commands

前置要求

  • Turso account with a database URL and auth token (TURSO_URL and TURSO_TOKEN env vars) for cold storage and critical sync
  • An LLM API endpoint or local model server for LLM-powered distillation and tree search (rule-based mode works without one)

安装

clawhub install bowen31337/tiered-memory

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接