surrealdb-knowledge-graph-memory
di maverick-software
Search & ResearchSintesi
A comprehensive knowledge graph memory system with semantic search, episodic memory, working memory, automatic.
Descrizione
Cosa fa questa skill
A knowledge graph memory system built on SurrealDB that stores semantic facts, episodic task histories, and working memory state for AI agents. Four scheduled background jobs extract facts from memory files, discover relationships between them, deduplicate, and prune stale data automatically. Each agent gets an isolated memory pool, with optional shared global facts.
Unlike static context files, the knowledge graph grows and refines itself on a schedule, so accumulated facts become progressively more connected and relevant without manual curation.
Quando usarla
- Retrieving decisions made in past coding sessions by semantic query
- Persisting project knowledge across separate agent conversations
- Running independent memory pools for multiple specialized agents
- Auto-injecting relevant context into prompts before each agent turn
- Calibrating fact confidence based on whether tasks succeeded or failed
Esempio di workflow
User asks: What did we decide about the authentication approach last month?
- 1
Calls knowledge_search with the user query against the SurrealDB vector index
- 2
Filters results to the active agent's fact pool plus any global-scoped facts
- 3
Traverses relates_to edges to surface connected facts from the knowledge graph
- 4
Formats matched facts and episodic memories via memory_inject for prompt injection
Agent responds with stored decisions, related facts, and past task learnings pulled from the knowledge graph
Requisiti
- OPENAI_API_KEY environment variable
- SURREAL_USER environment variable
- SURREAL_PASS environment variable
- SURREAL_URL environment variable
- SurrealDB (surreal binary) installed
Installazione
clawhub install maverick-software/surrealdb-knowledge-graph-memoryEsegui il comando CLI oppure incolla il prompt in Claude Code, Cursor, Codex o nell'agente di coding che usi.