Private AI Mesh · Edge Computing

Private

AI

Mesh.

Federated RAG across machines you own. Local LLMs via Ollama. Tailscale mesh networking. Nothing reaches the cloud.

0%

private by design

0ms

cloud API latency

0 cmd

to add a node

Scroll
Federated RAGTailscale MeshJWT AuthOllama LocalGGUF ModelsPrivate by DefaultE2E EncryptedZero CloudEdge ComputingWebSocket StreamsSecurity TiersSelf-HostedFederated RAGTailscale MeshJWT AuthOllama LocalGGUF ModelsPrivate by DefaultE2E EncryptedZero CloudEdge ComputingWebSocket StreamsSecurity TiersSelf-Hosted

The Platform

Three layers.
One mesh.

Every component is self-hostable, composable, and talks only over your private Tailscale network.

01

Orchestrator

Central brain

Preprocesses queries with llama3.2:3b, fans out to all Aligner nodes, reranks merged chunks, synthesizes final responses via llama3.1:8b streaming. JWT auth + RBAC.

Python · FastAPIport 8001ngrok tunnel
02

Aligner

Edge RAG node

Indexes your local files, serves security-filtered vector retrieval. Security levels enforced at source — the orchestrator never sees restricted chunks.

Python · Chromaport 8000Tailscale only
03

Client layer

Web UI + Tauri app

Browser WebSocket chat and a Tauri desktop dashboard. Connects to your orchestrator — no intermediary, no third-party relay.

Next.js · TypeScriptWebSocketSelf-hosted
01

How it works

Three steps to
your private mesh.

01

Install & pull

Run the orchestrator on any machine. Pull your Ollama models. Zero cloud configuration required.

02

Connect via Tailscale

Add nodes to the mesh with a single auth key. Encrypted WireGuard tunnels, no port forwarding.

03

Query your swarm

Send a prompt. It fans out to every node, reranks, synthesizes — streamed back in real time.

Capabilities

Everything
in one mesh.

Federated RAG

Fan-out to every Aligner node simultaneously. Merged, reranked results — zero data leaves your machines.

A
BA
CA
ZZ

Security tiers

Per-file, per-line access control enforced at the edge. The orchestrator never receives restricted data.

Local inference

llama3.1:8b on your hardware via Ollama. Zero API calls, zero data leaks, zero latency tax.

laptopdesktopserver

Tailscale mesh

Every node auto-connected over zero-trust WireGuard. New machines join with one command.

Streaming chat

Token streaming over WebSocket with interactive node-selection canvas. Pick exactly which nodes respond.

Voice input

Hold-to-record. Whisper transcription runs server-side — query your mesh hands-free.

Live demo

A real query.
Your machines.

Watch the orchestrator fan out to three nodes, rerank the results, and stream a synthesized answer — all on local hardware.

Input
Output
See the full API reference
0%

Private by design

No cloud API ever called

0ms

Cloud overhead

Everything runs on your hardware

0 nodes

Starter tier

Up to 15 on Growth plan

0 cmd

To join the mesh

Via Tailscale auth key

Pricing

Priced by nodes.
Not queries. Not data.

Starter

$19/mo

Up to 5 nodes

Get started

Growth

$49/mo

Up to 15 nodes

Get started

Enterprise

Custom

Unlimited nodes

Contact us

Build your private

AI mesh today.