تخطَّ إلى المحتوى
TakoAPI
العودة إلى المهارات

usewhisper-autohook

بواسطة alinxus

Coding Agents & IDEs
451التنزيلات وفق ما يذكره clawskills.sh
0المشاهدات
لا إعجاباتسجّل الدخول للإعجاب بهذه المهارة
—لم يُقيَّم بعد
تقييمك

موجز

Auto-hook tools for OpenClaw: query Whisper Context before every generation, ingest after every turn.

الوصف

ما الذي تفعله هذه المهارة

Auto-hook wrapper for OpenClaw that queries Whisper Context before each agent generation and ingests the completed turn after. Defaults to delta compression and caching to minimize token use. Works with any stable user_id/session_id pair, with Telegram as the primary target.

Delta compression with locally persisted context hashes prevents re-sending unchanged memory on every turn, so token use stays lower than with full-history approaches.

متى تستخدمها

  • Persisting user context across Telegram bot sessions
  • Recalling past decisions without replaying full chat history
  • Injecting compressed long-term memory into agent prompts
  • Reducing token costs on high-volume conversational agents
  • Running a memory proxy for frameworks that always send full conversation history

مثال على سير العمل

الإدخال

User asks: What did we decide about the project timeline last week?

الوكيل
  1. 1

    Calls get_whisper_context with user_id, session_id, and the current query

  2. 2

    Receives compressed context string from Whisper Context API

  3. 3

    Prepends context to the prompt as 'Relevant long-term memory: ...'

  4. 4

    Generates response using the injected memory

  5. 5

    Calls ingest_whisper_turn to store the user and assistant messages

الإخراج

Agent responds using past context; the turn is stored for future recall

المتطلبات

  • Whisper Context API key from usewhisper.dev (WHISPER_CONTEXT_API_KEY)

التثبيت

clawhub install alinxus/usewhisper-autohook

شغّل أمر واجهة سطر الأوامر، أو الصق النص في Claude Code أو Cursor أو Codex أو أي وكيل برمجة تستخدمه.

الروابط