Skip to content

Latest commit

 

History

History
66 lines (47 loc) · 3.06 KB

File metadata and controls

66 lines (47 loc) · 3.06 KB

MemSense Docs

Docs hub for onboarding, architecture, retrieval, and operations.

Start here: ../README.md


Reading paths

1) I want to try MemSense quickly

2) I want to understand how it works

3) I want to operate or debug it


System mental model

MemSense can be understood in four layers:

  1. capture — online interaction becomes memory chunks
  2. enrichment — embeddings, tags, and memory semantics are added
  3. retrieval — candidates are recalled with semantic + lexical signals
  4. selection — results are reranked for relevance, time-awareness, and diversity

That is the system meaning of:

From agent history to living memory.


Documentation map

Area Page What it covers
Product ../README.md Vision, story, quick start
Setup features/update-guide.md Update MemSense
Setup features/no-docker-quickstart.md Advanced macOS / Linux startup without Docker
Setup features/local-bge-oneclick.md Local embedding service
Architecture features/architecture-overview.md System flow and data movement
Retrieval features/retrieval-algorithm.md Dual recall, scoring, MMR-style selection
Retrieval features/embedding-search.md Compact search/storage summary
Ops features/dashboard-rbac.md Dashboard surfaces and RBAC
Ops features/worker-retry-dlq.md Worker reliability and job lifecycle
Validation features/api-smoke-test.md Runtime verification

Documentation principles

  • README.md sells the vision and gets people to try it.
  • docs/README.md tells people where to go next.
  • docs/features/*.md explains one concrete part of the system at a time.