v3.0 · Warm-Pool · Token-Streaming

Your AI, every tool you own
— one voice away.

Connect Claude, OpenAI, Gemini or a local model. Conduit pipes your AI through every MCP, every skill, your whole memory — one voice you can talk to from any device. Solo, or as a single shared brain for your whole company.

Reconcile invoicesTriage inboxReview PRSummarize meetingPull CRM deals

Free OSS · Cloud 9 €/mo (Q3) · Teams: 4-week paid setup

conduit.rainerroloff.de
v3.0
Reconcile last week's invoices against the bank statements and push the missing receipts.

Ask Claude anything…
Claude Opus 4.7 · 12 MCPs · 47 skills loadedbridge online · 3 ms
Account data hosted in Germany Auto-setup, no DIY Bring any AI account Mac · iOS · Android · Windows

Connected

Every tool you already use — wired into one brain.

Pick your AI (Claude, OpenAI, Gemini, or a local model). Conduit speaks the MCP protocol — anything that exposes one becomes a verb your AI can do, by voice, from any device.

Slack
GitHub
Notion
HubSpot
Microsoft 365
Google
Stripe
Supabase
Linear
Vercel
Figma
DATEV
OpenAI
+
200 more

Conduit for Teams

In development · onboarding design partners

Your AI. In your data room.

You’ll get your own AI instance in your own data room — hosted in Germany and built for GDPR (DPA/AVV available on request). Wired into your stack (DATEV, HubSpot, M365, …) with a shared company memory. Every employee accesses the same brain through Conduit — what a colleague feeds in today (processes, notes, customer info), the whole team uses tomorrow. The knowledge stays with you, and grows with every use.

Not another Cowork. Tools like Claude Cowork give one person a Claude-only agent in a US cloud, working on files on their own desktop. Conduit gives your whole team a shared brain — in your data room, hosted in Germany, wired into your stack, on the AI provider of your choice. The memory is the company’s, not one laptop’s — and it stays when people leave.

RR
AS
JK
MP
EL
Conduit
demo
Memory2.4k notes
Skills47 loaded
MCPs12 wired
Agents6 running
Hosted in Germany

Your AI instance will run in a Frankfurt or Berlin data center — or, on Enterprise, inside your own VPC or on-prem. With a local model, no US-cloud and no data crossing borders.

One memory, not 30

No more “ask the person who knows”. The knowledge sits in Conduit. A new hire on Monday is as productive as a two-year veteran by Friday.

Your stack, wired once

We build the MCP layer to your DATEV, HubSpot, Lexware, M365. Every employee gets the same access, the same way, by voice or by chat.

How a pilot works.

  1. 1We map your stack and define the first 3 MCPs to wire (typical: DATEV, HubSpot, M365).
  2. 24-week paid setup: AI instance in your data room, MCPs, skills, memory, per-team scopes.
  3. 3Monthly retainer for updates + new MCPs. You bring the Anthropic / OpenAI API key — we never resell tokens.

Tell us about your team.

How it works

Three pieces. No reseller in the middle.

1

Bridge on your Mac

A tiny daemon spawns your chosen AI's local CLI per request — claude, codex, gemini, ollama. SQLite log, JWT auth, warm-pool process. Runs on launchd, restarts itself.

2

Cloudflare Tunnel

Outbound-only WSS — no open ports, no inbound firewall holes. Auto-provisioned per account; TLS is terminated at Cloudflare's edge and message contents are never stored on our servers.

3

Conduit clients

PWA, native macOS, iOS/Android wrappers, Alexa skill. Live re-attach over WS so a 4G drop never breaks the answer mid-stream.

Why Conduit

What no other tool gives you.

ConduitClaude CoworkClaude.ai / ChatGPTCursor
Voice inPartial
Mobile / Alexa / CarPlayPartialPartial
Access your repos / shell / filesYour desktopEditor only
Your own MCP serversConnectors only
Your own skills + memoryPer-user
Same brain for the whole team
Provider-agnostic (Claude / GPT / Gemini / local)Claude onlyLocked-inLocked-in
Runs in your data room (DE / on-prem)
AI processing stays in-country (self-host / local model)US cloud

Pricing

Pay for the bridge. Tokens stay yours.

Bring your own Claude, OpenAI, Gemini or local-LLM account. We never resell tokens — we charge for the tunnel, the apps, and the convenience of having your AI everywhere.

Free
€0
forever · read-only
  • 1 Device
  • Full UI & history access
  • Auto-tunnel setup
  • Send a message → upgrade
Install Conduit
Solo
€14/ mo
€139 / year (–17%)
  • 3 Devices
  • Unlimited messages
  • Voice + text input
  • Any AI provider you bring
Start with Solo
Most popular
Max
€29/ mo
€290 / year (–17%)
  • Unlimited Devices
  • Hosted Whisper voice
  • Alexa skill ready
  • Multi-Bridge (Mac + iPad + Linux)
  • Priority support
Get Max
Teams
Early access
€690/ mo
10 Seats · scales to 100+
  • AI instance in your data room
  • Custom MCPs (DATEV, HubSpot, M365)
  • Per-team scopes & audit log
  • Requires API key (Anthropic / OpenAI)
  • Enterprise On-Prem from €4,990
Talk to us
Which AI account works? All consumer tiers (Free, Solo, Max) accept any AI you bring: Claude Pro/Max, ChatGPT Plus/Pro, Gemini Advanced, or a local model via Ollama. Teams and Enterprise run on an API key (Anthropic, OpenAI or your provider of choice) under the relevant Commercial Terms. We never charge for tokens — only for the bridge, the apps and the hosted layer.

FAQ.

Which AI does Conduit use?+

Whichever you bring. The bridge can spawn Anthropic's claude CLI, OpenAI's codex CLI, Google's gemini CLI, or a local model via Ollama — your choice in Settings. We never resell tokens; you connect your own account or API key. Switch providers anytime without losing your chats or memory.

What does the Free tier actually do?+

Free is read-only forever — you see the full UI, browse your chat history and memory, install the app on one device. To send a new message (voice or text), you upgrade to Solo or Max. No trial expiry, no credit card.

How is the bridge installed?+

When you install the Conduit app on your Mac for the first time, it auto-provisions a private Cloudflare tunnel for your account and starts the bridge as a launchd service. No DNS or Cloudflare setup on your side — just install and sign in.

Does my data leave my machine?+

Chat history lives in local SQLite on your bridge (your Mac) and we never store it. To generate answers, your prompts do go to whichever AI provider you connect (Anthropic, OpenAI, Google, …) — unless you run a local model, in which case nothing leaves. Between your phone and your Mac we only see encrypted WebSocket traffic, TLS-terminated at Cloudflare. Teams will be hosted in Germany — or your own VPC on Enterprise.

How can my whole team share one brain?+

Conduit for Teams is in development — we're onboarding design partners now. It will run one shared AI instance in your data room — hosted in Germany and built for GDPR (DPA/AVV available on request). Shared memory, skills, and MCPs (DATEV, HubSpot, M365, …). Each employee accesses the same brain; what one person feeds in today, the whole team uses tomorrow. Per-team scopes, audit log, and on-prem option are planned.

How is this different from Claude Cowork?+

Cowork gives one person a Claude-only agent that works on files on their own desktop, in Anthropic's US cloud. Conduit is built to give a whole team one shared brain — running in your own data room (Germany or on-prem), wired into your stack via your own MCPs, on whichever AI provider you bring. With Cowork the memory lives on a laptop and walks out the door when someone leaves; with Conduit the knowledge is the company's and compounds. They're complementary for a solo desktop task — but for a team that wants its own AI in its own data room, that's Conduit.

What if Anthropic / OpenAI / Google build their own mobile apps?+

They probably will — for their own model. Conduit is provider-agnostic by design. You can swap Claude for OpenAI for Gemini for a local model in Settings without losing memory, MCPs or chats. We're the layer that stays.