AI Infrastructure Company
Dweve is an AI infrastructure company building compute, reasoning, agents, developer tools, products and open foundations for explainable, replayable systems.
Choose the audience that matches your question
The page contains three selectable readings of the same subject.
For consumers
Fabric brings your questions, files, notes, links, mail, and calendar context into one private workspace. Ask in everyday language, inspect the sources behind an answer, and turn the work you repeat into a routine you can keep using.
For businesses
Dweve turns document-heavy work into a controlled flow from intake to approval. Sources, policy checks, exceptions, owners, actions, and evidence stay in one record, so operations can clear blockers and finance can measure the gain before scaling.
For engineers
A request begins as a durable Fabric object and invokes only the product boundaries the work needs. Agent, cognition, knowledge, policy, target, execution, and placement events return with the result, each tied to a named contract.
Dweve is the service: you use it through Fabric, the API and portal, and Loom is the model that answers.
Loom builds a path for your task. All 528 domain specialists are in production; 4–8 are active per query. Loom is deterministic on supported paths, with checking built into the path.
A draft to review. The next move is yours.
Stored and processed in Europe. From your first question to the work you keep. Billed by Dweve B.V. in the Netherlands, in euros.
Fabric Personal is for one person. Fabric Friends & Family covers five named people.
Independent Builder includes Fabric web/app and Aura CLI for one developer, with no direct API. For product or team API use, discuss Fabric API access with Dweve.
Start with a Business Workspace through Fabric, including the business API and Agent SDK, or scope metered direct API access with Dweve.
Pre-order Dweve. Access opens in phases. Next round: 1 November 2026. More rounds, then public launch. We will email you when your access is ready.
Free access through Mesh is only for Fabric Personal customers who have paid for at least one month and share compute.
Business Mesh uses credits for circular compute.
Fabric Friends & Family · five named people
Inputs, state and versions are captured for reproducible replay. Inspect the diff before using it.
Check: the file opens and reads back as written. Run and test the app yourself.
One work record · sources and evidence stay attached
The work record stays put: inputs, sources, approvals and evidence.
The 14 Rust foundations publish under Apache-2.0 on the dates shown. Loom, its specialist catalogue and its domain constraint sets are not open source.
Review AI output before you rely on it. Inspect the sources and checks, test changes, and decide what to use.
Your data is stored and processed in Europe. Dweve B.V. in the Netherlands bills you in euros.
Access opens in phases. Next round: 1 November 2026. More rounds, then public launch. We will email you when your access is ready.
Who can use Dweve for free through Mesh?
Only Fabric Personal customers who have paid for at least one month and share compute.
Discuss Fabric API access with Dweve. Scope a Business Workspace with the business API and Agent SDK, or metered direct API access.
Subject explanation · source reading · exercise planning · answer checking
Images, documents, files and other media become observations the reasoning core can use and later checks can cite.
Reasoning is separate from language generation. The plan sets out what must be true before the answer is written.
Every hard rule satisfied on the supported path. The certificate is attached for checking.
A small language model writes the answer
Deterministic on supported paths: the same input and captured state give the same answer.
Built to run efficiently with simple whole-number maths.
Every model runs on integer and fixed-point arithmetic, compiled to bitlanes or codebooks.
The small language model that writes the answer
Images and files are turned into details Loom can work with and check later.
Loom works out the steps and rules before a small language model writes the answer.
On supported tasks, the record shows that the plan meets every required rule. You can check it alongside the answer.
On supported tasks, the same input and the same saved information give the same answer.
Loom wrote a draft and checked the answer.
A rule check was unsure. Review the draft before sharing it with your team.
Domain specialists selected for each task
Offline proof certificates for AI decisions
Document runtime for reading, editing and recalculation
Binary hypervector engine for composable semantic data
FMI 3 runtime for interoperable simulations
Compact text format for structured LLM data
Signed, offline-verifiable audit trails for AI agents
Deterministic policy and constraint evaluation engine
Hash-chained event ledger for AI tool interactions
Deterministic fixed-point, decimal and integer arithmetic
Local code intelligence over reusable structural models
Deterministic WebAssembly sandbox with replayable execution records
Local, rule-based context compression before LLM calls
Event-sourced digital twins with historical state replay
Source-intelligence runtime for repeatable web collection
return Err(SessionExpired);
One request · explicit handoffs · evidence returned
The route changes with the work. The identity, contracts, and return path stay explicit.
Only the layers a request needs have to run. This view shows the complete path so every boundary can be inspected.
result + evidence return to the work surface
The products do not hide what they depend on
Only relationships asserted by the current product and open-source pages are drawn here. Absence from this ledger is not a claim that a foundation is unused.
Inside the product or a real dependency of it.
A supported integration, not an internal dependency.
Foundations with no product edge asserted in this view
Numerus, Signum, and Selvedge remain part of the 14 open-source routes. This ledger does not invent a product relationship where the current pages do not make one.
The route may shorten. The thread must not break.
Analyzed request, identified 3 key concepts
Retrieved context from the Dweve Loom knowledge base
F(n) rounds phi to the n over root five.
Ratios of terms approach phi, near 1.618.
The sequence appears across nature and tiling.
Iterative growth, linear in n, exact in integers.
Dweve Loom, Query Analysis, 3 domain specialists, 2 sources
Type a message or @ to mention an agent...
Fabric brings your questions, files, notes, links, mail, and calendar context into one private workspace. Ask in everyday language, inspect the sources behind an answer, and turn the work you repeat into a routine you can keep using.
One workspace for your context, answers, and recurring work.
Dweve turns document-heavy work into a controlled flow from intake to approval. Sources, policy checks, exceptions, owners, actions, and evidence stay in one record, so operations can clear blockers and finance can measure the gain before scaling.
Baseline one workflow, run real work, and compare the result.
A request begins as a durable Fabric object and invokes only the product boundaries the work needs. Agent, cognition, knowledge, policy, target, execution, and placement events return with the result, each tied to a named contract.
Inspect the representations, constraints, computation, placement, and claim boundaries instead of trusting a model name.
Start at the trace, the responsibility map, or a computation contract.
Fabric Personal is EUR 14.25 and Fabric Friends & Family EUR 35.63 for five named people, at launch pricing that stays fixed for the uninterrupted contract. Access is live in phased, invite-only rounds; the next round opens on 1 November 2026.
Choose real work with a known baseline, real documents, a named owner, and an approval. Compare cycle time, queue age, repeat work, exceptions, and evidence effort before deciding how far to expand.
Follow a request trace, inspect the system map, or test a handoff at the knowledge, policy, execution, or placement boundary. Judge the architecture by the state and evidence it returns.
Your personal Fabric interface. Chat with memory, upload files, build small assistants, and save recurring routines through the public Dweve Mesh.
No. Your conversations and files stay yours. We do not train models on your content, ever.
In the EU only. The Business Workspace uses EU-only paths on the public Dweve Mesh, so your data is not routed through other jurisdictions.
Fabric Personal is EUR 19 a month for one named person. Fabric Friends & Family is EUR 47.50 for five named people, the price of 2.5 Personal subscriptions. Both use Fabric through the web and app without Aura, direct API access or Agent SDK rights. The compute-contribution route is limited to eligible Personal customers after the first paid month.
Yes. Every answer shows where it came from. You can open the sources behind any response instead of taking it on faith.
Bring your mail, your calendar, your files, and the apps you use every day into one place, so Fabric can work with what is already there instead of starting from a black box.
Personal is EUR 19 a month and Friends & Family is EUR 47.50 for five named people. Their launch prices are EUR 14.25 and EUR 35.63. Both are billed by a Dutch entity and cancelable at any time. After the first paid month, an eligible individual Personal customer may instead use the compute-contribution route; Friends & Family is excluded.
Sovereign AI with clear deployment options.
European infrastructure under European law.
Private, on-prem, or air-gapped environments.
After the first paid month, eligible customers may use Fabric's published spare-compute route under its current terms.
EU jurisdiction, controlled deployment, no sovereignty asterisks
The review packet forms while the work moves. Source, rule, owner, and replay stay attached to the decision, so a later audit starts with evidence instead of reconstruction.
Can this decision still be defended after the people and systems around it have changed?