Agents inherit how your team works
Identity, values, and limits travel with the workspace - so every session starts with context, not a blank slate.
Your knowledge. Your way.
M
A
T
S
T
E
R
AI finally has somewhere real to stand. One place where your team's knowledge and its AI live together - so no one, and no agent, starts from zero.
Maater chat
Draft a plan for the checkout mobile fix work spec
checkout-mobile-fix.md
Sprint review - Jun 28
Here's a plan grounded in the work spec and last sprint review - acceptance criteria, risk notes, and a client-ready update draft.
On the name: say it like matter. Maat is order and truth, matter is what counts, mater is the source.
The problem
You added AI. You got more silos.
01
More AI, more silos
Every tool sprouts its own assistant. None can see across the others, so you patch the knowledge together by hand.
02
Your AI keeps forgetting
Every session starts cold. You re-explain the client, the plan, the history - to teammates, to stakeholders, to every tool.
03
The knowledge is in there somewhere
Buried in email, comments, transcripts, and threads. You spend more time finding it than using it.
The fix isn't another AI tool. It's one place your team - and its AI - can finally see.
See it work
One work spec, from plan to reusable knowledge.
A request - from wherever your work starts - seeds a work spec: the plan. It fills with decisions, status, and progress as the work runs, then becomes searchable knowledge the next task can build on. One artifact, its whole life.
01 Shape
A request becomes a work spec
Work starts somewhere - a Basecamp todo today, any system with an API and a flow trigger next. Its data seeds the spec, then layers in your existing project knowledge and the human part: context, decisions, hard-won judgment. Out comes a work spec, ready to dispatch.
Ingest
Request · via flow trigger
Fix broken checkout on mobile - Basecamp #8214 (or any API)
+ Project knowledge
Client history, past decisions, related work specs
+ Your input
Context, guidance, and the calls only you can make
shaped into ↓
Work spec - ready to dispatch
Stakeholder timeline, technical read, client-ready update
02 Execute
Any coding agent, over MCP
Bring the spec into your editor, beside your repo. Your agent has the whole codebase and an immaculate spec - so the code becomes the easy part. The work that mattered already happened: shaping the spec, setting the standards, challenging the plan. Any coding agent works from it over MCP; the Cursor / VS Code extension adds on-disk 2-way sync.
Coding agent · MCP
Implement the checkout mobile fix
get_work_spec
search
Building against the spec - acceptance criteria and last sprint's QA notes already in context.
03 Live & compound
The work spec becomes the record
As the work runs, the same spec fills in - decisions, status, review, related docs. Hit a client approval or an external blocker? Pick it back up weeks later and nothing's lost - it was indexed at ingest. And done isn't dead: the whole task history is one artifact, discoverable to the next task or agent that hits something similar.
checkout-mobile-fix.md
Work spec · done
status: done · review: passed · PR #214 merged
History captured
3 decisions logged, sprint QA notes, client stack constraints
decisions
related: cart-persistence.md
origin: Basecamp #8214
reused later ↓
A new task finds it
"Similar checkout bug" - the agent surfaces this spec first
Nothing you make lands outside the graph. Google Docs flow in and push back out. Zoom calls file themselves - transcript, summary, and action items attaching right to the work spec. Every tool you already use feeds one graph.
Living system
One shared brain for your whole team.
One half is soul - identity, values, and voice that cascade from you, your team, and each project, so your AI knows how the work gets done before you type a word. The other half is a knowledge graph, vectorized the moment each document lands, so anything the org knows is one semantic search away.
Specs, playbooks, living docs
Not just notes. Work has shape - origin, status, and enough structure for a colleague or an agent to pick up cold.
Ask AI to assemble a view
Compose a view over the work you already have - without building another spreadsheet that goes stale.
Automations on your knowledge
Steps run against your documents, soul, and agents - not a generic pipe between tools that do not know you.
Surfaces
Same knowledge. Pick your surface.
Surfaces are where you reach your knowledge - the same graph, wherever you work. Read and edit on the web, capture on your phone, or let your coding agent work with it in place over MCP. Open it anywhere - it's the same brain underneath.
Webapp
Team workspace + chat
Mobile
Quick capture, on the go
MCP
Any AI client · 30+ tools
VSIX Cursor / VS Code
Materialize + sync
Point any MCP client - Cursor, Claude Desktop, Claude Code - at Maater, and your whole knowledge graph is one toggle away.
Extensions
Maater is the spine. Extensions are the limbs.
Where surfaces are how you reach in, extensions are what Maater reaches out to - the tools where work already happens, plus your own systems over an API. Each is a real capability and integration point, not just a link out. First-party limbs ship with the product; custom limbs are how we meet your stack.
Maater
Basecamp
Google
Zoom
Git
Slack
Your API
Your AI
Your knowledge. Your AI. Your infrastructure. On your terms.
Sovereignty is how the product is built - not a premium checkbox. Pick what fits today; grow into more control when you need it.
Managed, or bring your own keys
Pick a model in chat with nothing to configure - or plug in your own Anthropic, OpenAI, or similar account. Your compute, your bill, your rate limits.
Bring your own endpoint, or self-host
Point Maater at your own inference - self-hosted or private cloud - or run the whole stack on your own hardware. Active track; we say path, not shipped.
How it's different
Not another notes app
The comparison that matters isn't feature count - it's what's true by default.
| Notion | Obsidian | Mem.ai | Maater | |
|---|---|---|---|---|
| AI indexed at ingest | Enterprise only | Plugin-dependent | Individual | Always |
| Built for teams | Yes | No | Limited | Yes |
| Work has a traceable origin | No | No | No | By default |
| BYOK / choose your AI | No | N/A local | No | Yes + path |
| Self-hostable | No | Files only | No | Path |
| Basecamp-native | No | No | No | Yes |
| Agent access (MCP for IDEs) | No | Community | No | Yes |
Early access
Make your knowledge maater.
A small group of teams is shaping Maater now - before the public launch. Bring your real work; help decide what ships.
No pricing yet. No spam. Just a seat while the product hardens.