
reef
Actively maintained
not read yet
Use
- For
- Households and small groups who want a shared memory their AI assistants can read, such as family or trip planning
- Activity
- Actively maintainedrelease 7 weeks ago
- Company
- Haai BVprivacy policy
- Runs as
- CLI
- Used for
- Keep a shared household list of allergies and trusted tradespeople
- Record household decisions so every AI chat already knows them
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsreefwith.me ↗
- Run byHaai BVprivacy policy ↗
- Trains on your dataNoprivacy policy ↗
- Privacy policy updated2026-08-11privacy policy ↗
“When you do that, the pages your assistant reads are sent to whoever runs it, and their privacy terms apply to that exchange — not reef 's. reef does not choose your assistant and does not send your pages anywhere on its own. reef does not train any model on your content.”
privacy policy ↗
These are reef's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP serverme.reefwith/reefverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-26
- Address to connectreefwith.me/mcp
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1

Plurality NetworkMCP · sign-in
Stores your preferences, writing style and knowledge in a user-owned memory that browser extensions and MCP pass into chatgpt, claude and gemini.
207Active - #2

Agentage MemoryMCP · open
Stores plain markdown memory files in an EU-hosted account and shares them with Claude, ChatGPT, Cursor and Claude Code over MCP.
190Active - #3

KeposMCP · sign-in
Gives several AI agents one versioned knowledge base over MCP, with a shared chat stream for coordinating handoffs.
2Active - #4

SkyOSMCP · sign-in
Stores short dated notes per project so Claude, ChatGPT and Codex can resume them in a new chat.
1ActiveFree - #5

KogniteMCP · sign-in
Hosted MCP server storing a shared knowledge graph that Claude, Cursor and other coding agents read and write.
1ActiveFrom $19/mo - #6

Context Engine
Stores decisions, notes and files that AI tools save and read over MCP, shared across a team.
2.4k linking domainsFrom $12/mo
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use reef for?
Sign in to leave a noteWhat is reef?
Stores shared markdown pages for households and groups, readable by Claude, ChatGPT and Codex over MCP. It is listed in the Atlas under Knowledge and made by Haai BV.
Who is reef for?
Households and small groups who want a shared memory their AI assistants can read, such as family or trip planning
Do people use reef?
Little sign of use.
Is reef still maintained?
Actively maintained: release 7 weeks ago.
Who owns reef?
reef is run by Haai BV, per its privacy policy (2026-10-26).
Does reef train AI on your data?
No, per its privacy policy (2026-10-26): “When you do that, the pages your assistant reads are sent to whoever runs it, and their privacy terms apply to that exchange — not reef 's. reef does not choose your assistant and does not send your pages anywhere on its own. reef does not train any model on your content.”
Is reef safe?
We do not audit vendors. What reef publishes, read 2026-10-26: on training with your data, “When you do that, the pages your assistant reads are sent to whoever runs it, and their privacy terms apply to that exchange — not reef 's. reef does not choose your assistant and does not send your pages anywhere on its own. reef does not train any model on your content.”.
What are alternatives to reef?
In Knowledge, by use: Plurality Network, Agentage Memory, Kepos, SkyOS, Kognite, Context Engine.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.