Pular para o conteúdo
TakoAPI
Voltar às skills

lily-memory

por kevinodell

Coding Agents & IDEs
899Downloads informados pelo clawskills.sh
2Estrelas
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Persistent memory plugin for OpenClaw agents.

Descrição

O que esta skill faz

Persistent memory plugin for OpenClaw agents that stores and retrieves facts across sessions using a hybrid SQLite FTS5 keyword search and Ollama vector semantic search. Automatically captures facts from conversations and injects relevant memories before each LLM turn. Includes stuck-detection to break repetitive loops and deduplication on startup.

Combines keyword and vector search in a single lightweight plugin without requiring a dedicated vector database, while falling back gracefully to keyword-only mode when Ollama is unavailable.

Quando usá-la

  • Remembering user preferences across separate agent sessions
  • Recalling past decisions when an agent restarts mid-project
  • Detecting when a conversation is looping on the same topic
  • Looking up all stored facts about a specific entity or config
  • Searching memory semantically when exact keywords aren't known

Exemplo de fluxo de trabalho

ENTRADA

User asks: What database did we decide to use for the API?

AGENTE
  1. 1

    Extract keywords from the question

  2. 2

    Run FTS5 keyword search against SQLite memory store

  3. 3

    Run vector similarity search via Ollama if available

  4. 4

    Merge and deduplicate results, inject top matches as context

  5. 5

    LLM answers using injected memory facts

SAÍDA

Agent recalls the stored fact 'api: database = PostgreSQL' and answers correctly without the user repeating themselves

Requisitos

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

Instalação

clawhub install kevinodell/lily-memory

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links