A local-first memory layer for coding agents to persist and retrieve project decisions, architecture context, and rules across multiple development sessions. It utilizes a three-tier memory model and hybrid retrieval to provide agents with durable, searchable context and a WebUI for human review.
A local-first memory engine for AI agents that stores embeddings in polar-quantized form in a single SQLite file, enabling private, compact, and human-like recall.
Gives AI coding agents persistent memory by storing observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine.
A local memory engine for AI agents. Stores conversation episodes, consolidates knowledge through a neuroscience-inspired lifecycle, and builds a personal knowledge graph — all in a local SQLite database.