Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

memento

bởi braibaud

Coding Agents & IDEs
427Lượt 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

Local persistent memory for OpenClaw agents.

Mô tả

Kỹ năng này làm gì

Memento adds persistent long-term memory to OpenClaw agents. It captures conversations, extracts structured facts via a configurable LLM, and injects relevant context before each agent turn. All data is stored locally in SQLite, and nothing is uploaded unless you opt into a cloud LLM for extraction.

Unlike cloud memory services, it keeps all data on-device in SQLite and supports fully local extraction via Ollama, so conversations never have to leave the machine.

Khi nào nên dùng

  • Remembering user preferences across separate sessions
  • Tracking decisions and action items from past conversations
  • Sharing knowledge between multiple agents on the same machine
  • Running fully offline memory using a local Ollama model
  • Migrating existing markdown memory files into a structured knowledge base

Quy trình ví dụ

ĐẦU VÀO

User asks: 'What did we decide about the database schema last week?'

AGENT
  1. 1

    Recall layer runs FTS5 keyword search against local SQLite facts

  2. 2

    Optional semantic embeddings surface related entries

  3. 3

    Matching facts are ranked by recency, frequency, and category weight

  4. 4

    Top facts are injected into the prompt via the before_prompt_build hook

  5. 5

    Agent responds using the retrieved context

ĐẦU RA

Agent accurately references the past schema decision without the user restating it

Yêu cầu

  • API key for Anthropic, OpenAI, or Mistral (only if using a cloud LLM for fact extraction)
  • Ollama installed locally (only if using local or air-gapped extraction)

Cài đặt

clawhub install braibaud/memento

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

Liên kết