Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

mindgardener

bởi widingmarcus-cyber

Coding Agents & IDEs
489Lượt tải do clawskills.sh công bố
2Sao
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Local-first long-term memory for autonomous agents.

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

User asks: remember everything from today's planning session

AGENT
  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

ĐẦU RA

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

Cài đặt

clawhub install widingmarcus-cyber/mindgardener

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

Liên kết