Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

usewhisper

bởi alinxus

Coding Agents & IDEs
505Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Official Whisper Context skill for OpenClaw.

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  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

ĐẦU RA

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

Yêu cầu

  • 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)

Cài đặt

clawhub install alinxus/usewhisper

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết