One prompt. Every model. Full transparency.
Talk to Claude, GPT, Gemini, and local models side by side. Every conversation stays on your machine.
A calmer way to work with many models.
Private by default
Conversations and keys live on your disk, never our servers. Run fully offline with local models.
Bring your own keys
Pay providers directly at cost — no markup, no subscription. Track spend per model in real time.
Compare side by side
Send one prompt to every model at once. See speed, tokens, and cost next to each answer — pick the best.
RAG over your files
Drop in your own documents and let any model answer from them. Source stays on your machine.
Image generation
Create images from a prompt with the same providers you already use.
Voice in and out
Speak your prompts and have replies read back — speech-to-text and text-to-speech built in.
Prompt library
Save, organize, and reuse your best prompts across every conversation.
MCP & tooling
Connect MCP servers and tools so models can take real actions, not just answer.
A real look inside Multivac.
Screens from the desktop app: first setup, inspecting tool calls, keeping an eye on what you spend, and the quick Ask window.
Bring your own keys
A short setup adds your first key to Vault, which lives in your OS keystore (Keychain, Credential Manager, or libsecret). Test it before you save. Requests go straight from your device to the provider with no proxy in between, and none of your content is sent as telemetry.
See exactly how an answer was made
The Readout lists every tool call in order with its status, timing, arguments, and raw results, next to a live Meter for the chat. When a tool needs your approval, the exact arguments are in front of you before anything runs.
Know what you spend
Meter tracks tokens, messages, and spend for every request, priced from a table you can edit. See daily spend, per-provider and per-model breakdowns, TTFB and p95 latency, and export to CSV whenever you want.
Every provider, one place
Connect Anthropic, OpenAI, Gemini, Groq, Mistral, DeepSeek, xAI, OpenRouter, Ollama, or any OpenAI-compatible endpoint. Each provider shows what its key unlocks and whether it still works, with tools, MCP servers, and the prompt firewall alongside.
Images and voice in Studio
Generate images, turn text into speech, and transcribe audio with the providers you already use. Every result shows its model, size, time, and cost, and is saved to your local app data folder.
Ask from any app
Press ⌥ Space over any app for a quick answer or a saved prompt from your library, then continue in Chat or open it as a Panel. Ask closes when you click away.
Your desk, not the cloud.
Multivac is a desktop app. There’s no account, no telemetry, and nothing leaves your machine except the API calls you choose to make.
Free. Private. Yours.
Multivac is available now for macOS, Windows, and Linux. Subscribe for release notes and new features — no spam.