Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

rune

bởi thebobloblaw

Notes & PKM
327Lượt 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

Self-improving AI memory system with intelligent context injection and adaptive learning.

Mô tả

Kỹ năng này làm gì

Rune gives an OpenClaw agent persistent memory stored in a local SQLite database. It dynamically selects relevant facts per conversation rather than loading everything at once, and applies forgetting curves so stale information fades over time.

Injects only contextually relevant facts per conversation instead of loading a full static context file, reducing token usage while keeping responses more accurate.

Khi nào nên dùng

  • Remembering why a technical decision was made weeks later
  • Getting prioritized task suggestions when unsure what to work on next
  • Tracking which tools or approaches caused problems in past sessions
  • Detecting when a project has stalled and needs attention
  • Adapting to whether a session is exploratory brainstorming or focused debugging

Quy trình ví dụ

ĐẦU VÀO

User asks: What should I work on next?

AGENT
  1. 1

    Runs rune inject to load relevant facts into session context

  2. 2

    Runs rune next-task to retrieve priority-scored task recommendations

  3. 3

    Checks rune stuck-projects to surface any blocked work

  4. 4

    Returns the top task with its priority score and relevant memory context

ĐẦU RA

Top recommended task with priority score, relevant project facts, and any identified blockers

Yêu cầu

  • Ollama installation (optional, required for local relevance scoring and fact extraction)
  • OpenAI API key (optional, for cloud-based reasoning features)
  • Anthropic API key (optional, for cloud-based reasoning features)

Cài đặt

clawhub install thebobloblaw/rune

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

Liên kết