usewhisper
por alinxus
Coding Agents & IDEsResumo
Official Whisper Context skill for OpenClaw.
Descrição
O que esta skill faz
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.
Quando usá-la
- 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
Exemplo de fluxo de trabalho
User asks: What did we decide about the retriever cache in our last session?
- 1
Run query_context with the user's question and session ID to retrieve compressed prior context
- 2
Inject the returned context into the model prompt instead of the full conversation history
- 3
Call the model and receive a response
- 4
Run ingest_session with the user and assistant messages to persist the turn to long-term memory
Agent answers using compressed prior context; the turn is stored and available for future sessions
Requisitos
- 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)
Instalação
clawhub install alinxus/usewhisperExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.