Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

lily-memory-plugin

bởi kevinodell

Coding Agents & IDEs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Persistent memory plugin for OpenClaw agents.

Mô tả

Kỹ năng này làm gì

Persistent memory plugin for OpenClaw agents that stores and retrieves facts across session resets, compaction, and restarts. Uses hybrid search combining SQLite FTS5 keyword lookup with Ollama vector embeddings for semantic similarity. Auto-captures facts from conversations and injects relevant memories as context before each LLM turn.

Combining keyword and semantic search in a single zero-dependency plugin removes the need to configure separate embedding infrastructure for most use cases.

Khi nào nên dùng

  • Remembering user preferences set in a previous chat session
  • Recalling a project decision made weeks ago without re-explaining context
  • Finding past facts about a specific entity using keyword or semantic search
  • Preventing an agent from looping on the same topic repeatedly
  • Maintaining continuity after an agent gateway restart

Quy trình ví dụ

ĐẦU VÀO

User asks: 'What database did we decide to use for the auth service?'

AGENT
  1. 1

    Extract keywords from the message and run FTS5 search against SQLite

  2. 2

    Run vector similarity search via Ollama using nomic-embed-text if available

  3. 3

    Merge and deduplicate results, inject top matches as context before the LLM turn

  4. 4

    LLM responds using injected memory context

  5. 5

    Auto-capture any new facts from the response and store them to SQLite

ĐẦU RA

Agent answers with the previously stored decision, e.g. 'You decided on PostgreSQL for the auth service on March 3rd.'

Yêu cầu

  • Ollama with nomic-embed-text model (optional, required only for semantic vector search)

Cài đặt

clawhub install kevinodell/lily-memory-plugin

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

Liên kết