跳到正文
TakoAPI
返回技能列表

neutron-agent-memory

由 naeemmaliki036 提供

Search & Research
—暂无评分
你的评分

简介

Store and retrieve agent memory using Neutron API.

描述

该技能的功能

Provides persistent memory storage for AI agents using the Neutron API. Saves text as searchable seeds and manages agent context objects across sessions. Supports semantic search to retrieve relevant past content by meaning rather than exact match.

Semantic search over stored seeds lets agents find relevant past context without needing exact keyword matches, which plain key-value stores cannot do.

何时使用

  • Remembering user preferences across separate agent sessions
  • Finding past conversation snippets by semantic similarity
  • Tracking episodic agent context for long-running workflows
  • Storing structured metadata alongside free-text memories
  • Persisting full conversation thread snapshots for later retrieval

示例工作流

输入

User asks: 'What did we discuss about blockchain last month?'

智能体
  1. 1

    Run semantic search against stored seeds with query 'blockchain'

  2. 2

    Retrieve top matching seeds above similarity threshold

  3. 3

    Pull associated agent context for session metadata

  4. 4

    Combine seed content and context into a coherent summary

  5. 5

    Return the relevant past discussion to the user

输出

Agent surfaces the closest matching conversation snapshots with blockchain content, ranked by semantic relevance

前置要求

  • NEUTRON_API_KEY environment variable
  • NEUTRON_APP_ID environment variable
  • Neutron account with API credentials

安装

clawhub install naeemmaliki036/neutron-agent-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