memento
by braibaud
Coding Agents & IDEsBrief
Local persistent memory for OpenClaw agents.
Description
What This Skill Does
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.
When to Use It
- 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
Example Workflow
User asks: 'What did we decide about the database schema last week?'
- 1
Recall layer runs FTS5 keyword search against local SQLite facts
- 2
Optional semantic embeddings surface related entries
- 3
Matching facts are ranked by recency, frequency, and category weight
- 4
Top facts are injected into the prompt via the before_prompt_build hook
- 5
Agent responds using the retrieved context
Agent accurately references the past schema decision without the user restating it
Requirements
- 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)
Installation
clawhub install braibaud/mementoRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.