Agents do not just need search. They need to remember preferences, unresolved loops, changing facts, and scattered evidence — then explain exactly where the answer came from.
Evidence is cited from the actual conversation, not hidden inside vector distance.
Each one is a thing real agents get wrong when memory is treated as generic semantic search.
ContextFit keeps that shape visible: tokens, chunks, metadata, memory atoms, and evidence-ranked episodes.
Preferences, goals, constraints, decisions, open loops, and temporal updates are different signals.
No embedding API is required. Retrieval runs on token-native structures you can inspect and move.
Markdown sections, TMD rows, JSON events, CSV rows, emails, and calendar events stay source-verifiable.
The result is not just a score. It is a ranked answer path with the chunks that justify it.
ContextFit is open source, local-first, and designed for the messy continuity layer real assistants need.