تخطَّ إلى المحتوى
TakoAPI
العودة إلى المهارات

mindgardener

بواسطة widingmarcus-cyber

Coding Agents & IDEs
489التنزيلات وفق ما يذكره clawskills.sh
2النجوم
0المشاهدات
لا إعجاباتسجّل الدخول للإعجاب بهذه المهارة
—لم يُقيَّم بعد
تقييمك

موجز

Local-first long-term memory for autonomous agents.

الوصف

ما الذي تفعله هذه المهارة

Local-first long-term memory for OpenClaw agents. Extracts entities from conversations into a wiki knowledge graph, scores events by surprise value, detects conflicts between new and old information, and assembles token-budget context. Everything is stored as markdown files with no database or external API required.

Unlike OpenClaw's built-in memory_search, which only queries existing memory, MindGardener creates and structures memory from conversations, adds surprise scoring, conflict detection, and graph traversal.

متى تستخدمها

  • Persisting project facts across multiple agent sessions
  • Flagging when new information contradicts stored knowledge
  • Building a navigable knowledge graph from conversation history
  • Injecting relevant context automatically at session start
  • Syncing per-agent memories to a shared store in multi-agent workflows

مثال على سير العمل

الإدخال

User asks: remember everything from today's planning session

الوكيل
  1. 1

    Run garden extract to pull entities and facts from the conversation

  2. 2

    Run garden surprise to score unexpected or high-value facts

  3. 3

    Run garden consolidate to merge new facts into the knowledge graph and detect conflicts

  4. 4

    Run garden inject --output RECALL-CONTEXT.md at the start of the next session to assemble relevant context

الإخراج

RECALL-CONTEXT.md populated with relevant facts within the token budget, ready to inject into the agent's context window

التثبيت

clawhub install widingmarcus-cyber/mindgardener

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

الروابط