跳到正文
TakoAPI
返回技能列表

usewhisper

由 alinxus 提供

Coding Agents & IDEs
505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

Official Whisper Context skill for OpenClaw.

描述

该技能的功能

A Node-based helper for OpenClaw agents that reduces context token usage via delta compression and caching. Before each model call, agents query packed context; after replying, they ingest the turn to build persistent memory across sessions.

Combining delta compression, caching, and cross-session memory in a single script lets agents cut token spend without restructuring their prompting logic.

何时使用

  • Cutting LLM API costs on long-running agent workflows
  • Persisting user preferences and past decisions across sessions
  • Retrieving only relevant prior context for a specific query
  • Tracking token savings and API spend with cost analytics
  • Pre-warming cache for predictable high-traffic agent queries

示例工作流

输入

User asks: What did we decide about the retriever cache in our last session?

智能体
  1. 1

    Run query_context with the user's question and session ID to retrieve compressed prior context

  2. 2

    Inject the returned context into the model prompt instead of the full conversation history

  3. 3

    Call the model and receive a response

  4. 4

    Run ingest_session with the user and assistant messages to persist the turn to long-term memory

输出

Agent answers using compressed prior context; the turn is stored and available for future sessions

前置要求

  • Whisper account and API key — set as WHISPER_CONTEXT_API_KEY
  • Project name for WHISPER_CONTEXT_PROJECT (auto-created on first use if it does not exist)

安装

clawhub install alinxus/usewhisper

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