The technology

Distributed compute exists. We're building the part that's missing: trust.

The Sarv Grid is a trust and orchestration layer for AI compute. It verifies every node before it earns work, isolates every workload while it runs, wipes every trace when it finishes, and accounts for every job it settles. That's what turns a million strangers' machines into infrastructure.

The pipeline

One request. Eight proofs.

Every job that enters the Grid walks the same path. No shortcuts, no exceptions for convenience. This is the engineering target the 100-Vault pilot is built to harden and measure.

01
Request
A client submits a job — embeddings, batch inference, media processing, scheduled agents.
02
Attestation
Each candidate node proves it's genuine hardware running signed, untampered software.
03
Verification
The scheduler matches the job's policy to nodes that can prove they satisfy it.
04
Isolation
The workload is sealed in an ephemeral enclave, encrypted end to end.
05
Scheduling
Placement follows price, carbon and local generation — compute follows energy.
06
Inference
The job runs, architecturally blind to the owner's files, keys and assistant.
07
Zeroisation
Enclave destroyed, keys wiped, memory cleared. Nothing persists between jobs.
08
Settlement
Compute is metered, logged and auditable — the network accounts for itself.
Verified sealed wiped accounted Evidence status per claim: Trust & Security

The supply side

Idle capacity becomes verified infrastructure.

The Grid's capacity comes from machines people already own — starting with the Sarv Vault. Household life always has priority; only genuinely unused, attested capacity is ever offered.

A node proves itself

Before any work flows, the Vault attests: genuine hardware, signed software, untampered state. Owners choose how much capacity to offer: Private Balanced Full

The Grid verifies and matches

Jobs are split, encrypted, and placed only on nodes whose attestation satisfies the job's policy — geography, hardware class, privacy tier.

Work runs sealed

Each job executes in an ephemeral enclave — designed to have no access to the owner's data, keys or life — and is zeroised on completion. See the wall →

Everything is accounted for

Every job is metered and logged. Owners see exactly what their hardware did and earned; clients can audit where their workload ran.

First workloads

Honest about what the Grid is for — and what it isn't.

A distributed network of home devices will never beat a hyperscale data centre at latency-critical work. So we don't chase it. The Grid starts where it genuinely wins: delay-tolerant, batch, privacy-hungry compute.

BUILT FOR

Embeddings & indexing

Turning document libraries into searchable knowledge — overnight, in bulk.

Batch inference

Large queues of model calls that can run over hours, not milliseconds.

Media processing

Transcoding, transcribing and analysing audio and video libraries.

Scheduled agents

Automated work that runs while the world sleeps — reports, monitoring, research sweeps.

NOT FOR

Real-time serving

Live chat at scale, gaming, trading — latency-sensitive work stays in data centres.

Frontier model training

Training the largest models needs dense interconnect the Grid doesn't have.

Unvetted workloads

No anonymous code, ever. Every workload class is reviewed, signed and policy-bound before it touches a Vault.

Sovereignty

You set the rules.

Know where your data runs, who it runs for, and under what conditions. Policies aren't promises in a PDF — they're enforced by the scheduler itself. A job that doesn't fit your rules never reaches your Vault.

And for organisations with obligations — public sector, healthcare, defence-adjacent research — sovereign compute isn't a preference. It's a requirement the centralised cloud answers with fine print. We answer it with geography and hardware.

Policy controlWhat it means
UK onlyWorkloads and data never leave the country.
Verified hardwareJobs run only on attested, genuine Vaults.
Private workloadYour job is never co-resident with others on a device.
Renewable preferredSchedule to Vaults with clean local power first.
Customer keysResults encrypted to keys only you hold.

Why it can win

The capacity already exists. The trust layer doesn't.

£0
Marginal cost of the building, the land and the grid connection — the Vault's owner covered those the day they moved in.
450K+
Nodes already contributing to distributed compute networks globally — the behaviour is proven, the trust layer is not.
Reference: SaladCloud (gaming-PC network, 191 countries)
Every
home
The addressable footprint. No planning permission, no grid queue, no new building required.

Existing decentralised networks — Akash, io.net, Render and others — already sell raw spare capacity. What none of them answers is the question that unlocks the valuable work: how do you safely run sensitive AI inference on a computer owned by a stranger? Attested hardware, sealed workloads, zeroisation and auditable settlement — that combination is the moat we're building. See how we test it →

The economics, in the right order

Owner earnings are a consequence — not the product.

The chain runs one way: private AI makes the Vault worth owning; the Grid makes idle capacity verifiably safe to use; utilisation makes the network valuable; only then do owner economics matter. When that works, a Vault owner shares in what their hardware earns — illustrative scenarios put it at £0–60/month*, measured honestly in the pilot, including the possibility it's £0.

If the model only works as "earn money from your box", it doesn't work. That's crypto-mining economics without the crypto. The pilot's retention-at-£0 test exists precisely to prove the value stands without the income.

Join the network

Trusted compute needs
trusted nodes. That's you.

Grow the Grid