Observed by Atlas — nobody has proved they control this domain. Is it yours?
DocuMemory
OBSERVEDDistils AI chat sessions into reusable architecture docs
- FRESHNESS
- 0.97
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 0
- BOT-FILTERED
- FIRST SEEN
- OCT 19
- IN THE FLOW
DocuMemory is a memory engine for AI-first engineers that passively distils raw AI chat sessions into permanent architecture decisions and reusable, prompt-injectable context blocks. It integrates with AI clients like Claude Code, ChatGPT, Cursor, and Windsurf via the Model Context Protocol, allowing capture, search, and recall of engineering knowledge directly from the AI client. It is intended to be self-hosted for teams that want to keep their knowledge on their own infrastructure.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
15 uses, once per account · Explore your workspace and connect your AI client · Distillation and Enhance with AI share the free allowance
US $12 billed monthly · Continue after your free uses with documents, AI integrations, and private uploads · Cancel renewal from Settings
US $120 billed annually · Save US $24/year · Continue after your free uses with documents, AI integrations, and private uploads · Cancel renewal from Settings
per month, or US $150 per seat, billed annually · 2-seat minimum · One shared documentation repository for your team · Every member gets a seat; share projects with everyone or restrict them to specific people · No free trial: billing starts when you set up the organization
Every crawl is diffed. Material changes are listed.
Nobody has vouched for DocuMemory yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about DocuMemory? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it