remember

Solid

Save an explicit scoped memory through Signet. Use only when the user clearly asks to remember something or when a tool/harness must persist an explicit memory row.

AI & Automation 226 stars 39 forks Updated today NOASSERTION

Install

View on GitHub

Quality Score: 81/100

Stars 20%
78
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /remember Use this skill for explicit memory writes. Do not use it as a general extraction, ontology, or dreaming path. Signet's current memory model is source-backed and scoped. A direct remember call creates or deduplicates a memory row, records provenance fields when provided, embeds the content when the daemon can, links mechanically recognizable mentions to existing same-agent entities, and enqueues the normal pipeline work. Raw text does not automatically create new ontology entities, aspects, grouped claims, dependencies, or supersession chains. ## When To Use Use `/remember` when: - the user explicitly says to remember, save, persist, or store something - a harness compatibility path needs to write an explicit memory inside a session - you need a durable recall row with clear tags, hints, scope, or provenance - you are importing a single explicit fact and can supply source metadata Do not use `/remember` when: - the task is ontology maintenance or dreaming; use the `dreaming` skill and `signet ontology ...` commands - the task is source ingestion; use `signet sources ...` or the connector import path so provenance remains inspectable - the content is a vague behavioral lesson; propose an AGENTS.md, identity, or skill patch instead - the user did not ask for persistence and normal session capture is enough ## CLI The common path is the CLI wrapper: ```bash signet remember "<content>" ``` Useful options: ```bash signet remember "<content>" --agent ...

Details

Author
Signet-AI
Repository
Signet-AI/signetai
Created
5 months ago
Last Updated
today
Language
TypeScript
License
NOASSERTION

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category