Skip to main content
Glama

search_nodes

Search a knowledge graph by combining keyword matching with semantic similarity, re-ranking results based on recency, project affinity, and other contextual signals.

Instructions

Search the knowledge graph using hybrid BM25 + semantic search.

When sqlite-vec is installed, combines FTS5 keyword matching with vector cosine similarity via Reciprocal Rank Fusion. Falls back to FTS5-only otherwise. Results are re-ranked with 6 contextual signals (recency, project affinity, graph proximity, richness, canonical facts, session).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
projectNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RMANOV/sqlite-memory-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server