Privateer (privateer.pro) puts frontier models and real working agents
in one place. Chat, generate images and video, then hand the work to an
agent — command it from your phone, put it on a schedule, or host it in
Harbor. Encrypted on your device or in our cloud, with inference on
hardware-attested enclaves.
Privateer is for everyone who refuses to choose between capable AI and
their privacy. Your conversations are encrypted on your device or in our
cloud, and every AI request runs through zero-data-retention providers
that never store or train on your prompts. Frontier models and real
agents, without giving up your data.
Builders & developers
Link any terminal — your laptop, a server, the desktop app — and it
becomes an agent you can drive from your phone. Approve each action
or let it run unattended, and get the finished files back.
Operators & solo teams
Put recurring work on a schedule and let routines run without you.
Bridge an agent into Telegram, Slack, Discord, or WhatsApp and
message it like a teammate.
Anyone with sensitive work
Keep everything on-device, or in our cloud encrypted with a key
derived from your password or wallet. Turn on Sealed mode and your
prompts go straight to a hardware enclave your device verifies.
Chat Interface
Ask anything and get clear answers. Attach images, documents, and files
to give every reply full context. Your conversations are saved securely,
so you can pick up exactly where you left off.
privateer.pro
Your Data, Your Rules
Keep data in the cloud or fully on-device — all encrypted. Your data
belongs to you, and only you. And you don't have to take our word
for it.
Encrypted on your device or in our cloud
Zero-retention inference via trusted execution providers
Names, emails & personal details redacted before the AI sees them
Turn on Sealed mode and your prompt is encrypted on your device straight
to a hardware secure enclave. Our relay routes and meters it, but can't
read your prompts or replies — inference is served by Sealed providers
like Tinfoil and Phala. And you don't have to take our word for it: your
device verifies the enclave's hardware attestation on every response.
Prompts encrypted on-device, straight to the enclave
A blind relay — we route and meter, but can't read your traffic
Client-verified hardware attestation on every response
Branch any conversation into a living board — explore ideas side by side,
add images and notes, and pinch and pan to see how your thinking connects.
Access Multiple Models
Choose from hundreds of models across every major provider — OpenAI,
Anthropic, Google and more. Search, filter, and switch anytime to find
the right fit.
Turn a prompt into a finished image or short video in seconds — then edit
it with AI. Just describe the change, dial in aspect ratio, resolution,
and style, and refine until it's exactly right.
One account, every major provider. Chat with hundreds of models — GPT,
Claude, Gemini, Grok, Llama, Mistral, DeepSeek, Qwen and more — plus image
and video generation. Switch anytime in the app, or call any of them by ID
through the OpenAI-compatible API.
Moonshot AI's newest frontier model — Kimi K3 — is live on Privateer.
With its sharp agentic reasoning and standout coding, it's built for
turning a single prompt into something you can actually run. Ask it to
design a game and save the result as Cargo: a playable build stowed
encrypted in your hold, ready to play, tweak, or hand to a friend through
a private link. Chat with it as privately as every other model —
encrypted on your device or in our cloud, with zero-data-retention
inference.
Ask for something real — a web page, a slide deck, a game, a document, or
a spreadsheet — and save the result as Cargo. Every build is stowed
encrypted in your hold, ready to run, edit, or download anytime — or
share it with anyone through a private link.
Web page
Slide deck
Mini game
Document
Code in Your Terminal
Privateer comes to your command line. The CLI is a coding agent that
reads, writes, and runs code across your projects — signed into your
account, so there's no API key to manage. Link a terminal to the app to
drive it from your phone, approve its actions, and send it files.
Every terminal you link becomes an Agent you can drive from your phone or
the web. Send it a prompt, watch it work in real time, and approve each
action — or give no quarter and let it run to the finish. Bridge it into
your team chat, too — Telegram, Slack, Discord, or WhatsApp — and message
it like a teammate, approving its actions right in the thread. It sends
finished files straight back to you, and you can take over driving it from
any device.
api-server
no quarter · off
Add rate limiting to the API and run the tests
Editing server/middleware/rateLimit.js and wiring it into the router.
Approve this action?
$ npm test
AllowDeny
Running tools…
Manage every agent from the app
Live view & approvalsNo quarter — run unattendedExtensions & skillsScheduled routinesChat via Telegram, Slack & WhatsAppResults via app, live or emailSend & receive filesTake over across devices
Privateer on your desktop
A native desktop app for macOS and Windows — the full Privateer
environment in its own window, with a local agent that can read, write,
and run code in a folder you grant it. Same account, same encryption;
your keys never leave your machine.
First launch: on macOS, right-click the app and choose Open once
(the build isn't notarized yet, so Gatekeeper asks the first time). On Windows,
if SmartScreen appears, click More info → Run anyway.
Runs on
macOS (Apple Silicon & Intel)Windows 10 & 11Local agent in a folder you grantYour keys stay on-deviceConnect your MCP servers
Harbor — An Agent That Never Sleeps
Don't want to keep a terminal running? Harbor hosts your Privateer agent
in our confidential cloud — always on and reachable from your phone or the
web, with your MCPs, tools, credentials, and scheduled routines. It runs
inside a hardware TEE we can't read into, the same posture as our Sealed
inference. Included on Navigator and above.
Runs in an attested enclave · Preview
What you get
Always on — no laptopYour MCPs & toolsYour API keys & credentialsRoutines & schedulesTalk from phone or webZero data retention
An OpenAI-compatible developer API, billed to your Privateer account.
Point your existing OpenAI client at our base URL, drop in a
sk-priv-… key, and reach hundreds of chat, vision, image,
video and audio models through one endpoint. Inference is a stateless
pass-through — we persist only billing metadata, never your prompts or
the responses.
Privateer goes wherever you do. Use it on your phone or right in the
browser — and with cloud storage, your encrypted conversations, projects,
and boards stay in sync across every device.
privateer.pro
Questions, Answered
Straight answers to what privacy-minded people actually ask.
Is Privateer a private AI chat app?
Yes. Privateer is built privacy-first: your content is encrypted on your device or in our cloud, chat inference runs with zero data retention through trusted execution providers, and a public transparency layer lets you verify how it works.
Can Privateer read my conversations?
Your content is stored encrypted — on your device in local mode, or in our cloud. Generating an AI response processes the request transiently through our server and model providers under zero-data-retention terms; inference traffic is not kept or used for training.
What AI models can I use?
Hundreds of chat models across every major provider — GPT (OpenAI), Claude (Anthropic), Gemini (Google), Grok, Llama, DeepSeek, Mistral, Qwen, Kimi K3 (Moonshot AI) and more. Plus image models like FLUX, Nano Banana, DALL·E 3, Ideogram, Recraft and Stable Diffusion 3.5, and video models like Veo 3.1, Kling, Runway Gen-3, Luma Ray 2, Seedance and Wan. See the full model list, with the exact IDs and pricing you can call through the API.
Can I build a game with Kimi K3?
Yes. Kimi K3, Moonshot AI's newest frontier model, is available on Privateer and is a strong fit for interactive builds. Describe the game you want and save the result as Cargo — a playable build stowed encrypted in your hold that you can run, edit, or share through a private link. The same works for web pages, slide decks, documents and spreadsheets.
Can Privateer generate images and video?
Yes — generate images with FLUX, Nano Banana, DALL·E 3, Ideogram, Recraft or Stable Diffusion 3.5, and video with Veo 3.1, Kling, Runway Gen-3, Luma Ray 2, Seedance or Wan. Edit with AI until it's exactly right, and with Cargo a description becomes a web page, document, spreadsheet, or mini game you can save and share.
How do I sign in?
With an email and password, or with a Solana wallet. No Google account required.
What if I forget my password?
There is no password recovery, by design. Your encryption key is derived from your password or wallet, so losing it means losing access to your encrypted data. Keep it safe.
Is there a private AI coding agent for the terminal?
Yes — the Privateer CLI is a coding agent that reads, writes, and runs code across your projects, signed into your account with no API key to manage. It supports MCP servers, custom skills, scheduled routines via the daemon, and BYOK (bring your own key) if you'd rather use your own provider credentials. It runs on macOS, Linux, and Windows with a self-contained installer that needs no Node — curl -fsSL https://privateer.pro/install.sh | sh (macOS/Linux) or irm https://privateer.pro/install.ps1 | iex (Windows PowerShell). Full details at privateer.pro/cli.
Can I control the coding agent from my phone?
Yes. Link a terminal to your account and it appears as an Agent in the app. Drive it from your phone or the web: send prompts, watch it work live, and approve each action — or give it "no quarter" to run unattended until the task is done (dangerous commands still ask). You can also bridge it to Telegram, Slack, Discord, or WhatsApp and message it like a teammate, allow-listing exactly who can reach it. It sends finished files back to you, and you can manage its extensions, skills, scheduled routines, and messaging channels, or take over driving it from any device.
Does Privateer support MCP?
Yes. The CLI agent connects to MCP (Model Context Protocol) servers, so it can reach your tools — databases, GitHub, internal APIs — while keeping the same account-based privacy model.
Can inference run in a Trusted Execution Environment (TEE)?
Yes. When you're signed in, supported models can run inside a hardware Trusted Execution Environment — Intel TDX, NVIDIA Confidential Computing or AMD SEV-SNP, through confidential-compute providers like Tinfoil, Phala and NEAR AI. Your prompt is decrypted only inside the secure enclave, and every response carries a hardware attestation you can inspect right in the app.
What is Sealed mode?
Sealed mode makes our server a blind relay. Instead of sending your prompt to us in plaintext, your device encrypts it straight to an attested hardware enclave, so we can route and meter the request but can't read your prompts or the model's replies. Your device verifies the enclave's hardware attestation on every response — so "we can't read it" is provable, not just promised. Sealed inference is served by providers like Tinfoil and Phala. A small amount of metadata still transits our server — a derived search query, the model you chose, and token counts for billing — but the conversation itself never leaves your device in the clear.
What is Harbor?
Harbor hosts your Privateer agent in our confidential cloud, so you get an always-available agent — routines, schedules, tools, and interactive chat — without keeping a terminal running on your own machine. It has access to your MCPs, APIs, and credentials, and you talk to it from your phone or the web. A Harbor agent runs inside a hardware TEE (AMD SEV-SNP) we can't read into; between-user isolation on a shared host is software-enforced. Harbor is a Navigator-and-above feature and is rolling out in preview — join the waitlist and we'll let you know the moment it's ready. Prefer to run it yourself? The Privateer CLI runs the same agent on your own machine.
Is there a developer API?
Yes — an OpenAI-compatible API billed to your Privateer account. Point your existing OpenAI client at https://api.privateer.pro/v1 with a sk-priv-… key (create one under Settings → API keys) to reach hundreds of chat, vision, image, video and audio models. It's pay-as-you-go — billed to your account credit, with per-model rates here. Inference is a stateless pass-through: we persist only billing metadata, never your prompts or responses, and requests are pinned to zero-data-retention providers by default. Full reference at docs.privateer.pro.
What platforms does Privateer run on?
Android via Google Play, iOS, the web app right here at privateer.pro, and a CLI coding agent for your terminal.
Chart your own course.
Your voyage starts here — free on web, iOS, and Android.
Tinfoil
Phala
NEAR AI
Intel TDX
NVIDIA Confidential Computing
AMD SEV-SNP
GPT
Claude
Gemini
Grok
Llama
DeepSeek
Mistral
Qwen
Kimi K3
FLUX
Ideogram
Recraft
Stable Diffusion 3.5
Veo 3.1
Kling
Runway Gen-3
Luma Ray 2
Seedance
Wan
Z.ai
MiniMax
