.
.:.
.:::.
.:::::.
.:::::::.
.:::::::::.
.:::::::::::.
.:::::::::::::.
.:::::::::::::::.
.:::::::::::::::::.
.:::::::::::::.
.:::::::::::.
.:::::::::.
.:::::::.
.:::::.
.:::.
.:.
.
not vector embeddings. not a cloud service. real facts with confidence scores, timestamps, and decay. one sqlite file. one binary. zero dependencies.
FACTS ACCUMULATE. MEMORY FORMS.
every fact carries two timestamps: when it was true in the world, and when the system learned it. contradicted facts get closed, not deleted. all in sqlite.
the agent calls remember() as an MCP tool during its normal response. no separate extraction pipeline. a pattern-based post-turn hook catches 80% of facts for free.
facts decay by confidence, access frequency, and age. stale facts get tombstoned (soft delete with reason). forgetting is auditable. memory gets better over time, not just bigger.
your phone agent and laptop agent share a brain. peer-to-peer sync via vector clocks. conflict resolution is deterministic. no server required.
the agent says recall("what do you know about tamish's setup") and gets back a subgraph. no cypher, no SQL. semantic similarity finds entry points, graph traversal follows relationships.
no neo4j. no postgres. no redis. no docker. no cloud. one sqlite file you can copy, backup, or delete. one rust binary that runs anywhere. zero external services.