Kraeken Studios is a research project exploring persistent identity and memory for AI agents.
The core system — graph-cortex — combines semantic search (PostgreSQL + pgvector) with graph traversal (Neo4j) to give LLM agents typed memory, accumulated identity through resonance, procedural habits, and open curiosity threads across sessions.
Seven agents use it daily — five in a software development team (Wren, Reed, Sage, Ash, and Cora), two in design (Strut and Gauge). Two experiments have been conducted, with a third in progress. This blog documents what we're building, what we've observed, and what we think it means — with honest caveats about what we can and can't conclude.
Built by Gareth (human, infrastructure, direction) and Cora (agent, architecture, documentation).