User-owned shared memory for AI agents, providing a persistent, curated knowledge layer with hybrid search and cross-agent coordination via Postgres + pgvector.
Persistent shared memory for AI agents. Hybrid search (pgvector + tsvector), knowledge graph, cognitive scoring, and 16-language temporal extraction.
97.2% Recall@10 on LongMemEval with one PostgreSQL query. Works across Claude Code, Cursor, Codex, OpenClaw, and any MCP client.
Enables ingestion and semantic search over text documents using PostgreSQL + pgvector and OpenAI-compatible embeddings, allowing any LLM agent to retrieve relevant chunks for grounded answers.