Content & SEO
Drafts one useful article a day for your site (or LinkedIn, Medium or a newsletter if you have no site yet), checks how you show up in search, and can open the post as a pull request for you to approve. Never publishes by itself.
FreePivra Desk 0.2.15 for Mac and Windows
Your busywork, drafted on your own computer.It asks before it acts.
Articles, invoice reminders, research briefs, study plans, cover letters: give an agent the job and it works from your files and apps, on routines you switch on. It waits for your yes before it sends, pays or changes anything. Use any model, including one running on your own machine.
Download for Macv0.2.15 · Apple silicon · 150 MB
Download for Windowsv0.2.15 · Windows · 138 MB
Jobs it does today
Start from a job you already know. It asks the rest.
Six templates ship in the app. Each asks a few setup questions and says plainly what it will not do. Schedules stay off until you tick them on. Money is never moved on its own.
Bookkeeper
Keeps a ledger from the invoices and receipts you share, tells you what is due, and drafts polite reminders you approve. It never pays, files or sends anything on its own.
Researcher
Looks things up on the web and in your files and writes a short brief with a link to every source. Says when sources disagree instead of guessing.
Job hunt
Tracks your applications, tailors your CV and cover letter to each role from what is true, and reminds you to follow up. You send everything yourself.
Study planner
Turns your syllabus and exam dates into a daily plan and quizzes you from your own notes, citing the file for each answer.
Social media
Turns your posts, news and wins into ready-to-copy drafts for LinkedIn and X, in your voice. Drafts only: you copy and post.
How it works
Give it a job. Let it run. Say yes.
- ResearchInvoicesContent
Step 1
Give an agent a job
Start from a template (Bookkeeper, Researcher, Content & SEO, Job hunt, Study planner, Social media) or describe the job in plain words. Each agent browses in its own browser profile.
Step 2
Talk to it, then let it run
Chat to set it up. Add routines on a schedule and let it follow up on its own. It keeps working in the background while the app is open and your computer is on.
Step 3
Approve what matters
Reading and searching just happen. Anything that sends, publishes, pays or changes something waits for you, in the app or on a card in your own Slack or Teams bot.
What it does
Real work. On a machine you control.
Everything an agent needs to get through a to-do list, and nothing that takes your data somewhere you did not choose.
Routines
Schedules and follow-ups that run in the background while your computer is on. Polls GitHub and your calendar for what changed.
Approval cards
Every send, publish, payment or change shows exactly what will happen before it does. A "never" rule you wrote stops it at once.
Any model, including none of ours
Offline mode with a built-in local model, or your own key for Anthropic, OpenAI, OpenRouter or any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM).
Sandboxed commands
On a Mac, commands run in the operating system’s own sandbox with network limits, no Docker needed. On Windows they use Docker for now.
Own browser profiles
Each agent browses in its own profile on your computer, separate from yours. You can take over at any moment.
Sealed credentials
Keys and logins are sealed in a vault on your machine. With your own key, nothing goes through Pivra’s servers.
Slack and Teams
Connect your own Slack or Teams bot and answer approval cards from your phone. Teams needs a public address for now; the Pivra relay for that is coming.
Voice calls
Talk to your agents out loud in the app, with an OpenAI key.
Connect your apps
Google Calendar (read only) and GitHub with one-click sign-in on Plus, remote and local MCP servers with sign-in, and Gmail with your own Google app.
Your model, your choice
On-device by default. Your own key when a job needs more.
Default
On this computer
Offline mode runs Gemma 4 (E2B, E4B or 12B) or a small Qwen model through llama.cpp on your own machine. No key, no account. Model files download from Hugging Face and are checked against a pinned checksum before use.
Best for reading, summaries and short tasks. Picks a size that fits the memory you have free.
Your own key
Anthropic, OpenAI, OpenRouter, or any OpenAI-compatible endpoint, including Ollama, LM Studio or vLLM on your network. Requests go straight from your computer to that provider.
Best for long, multi-step work.
Plus + Credits
Coming soon: Plus, with cloud model credits included so you can start without a key of your own.
For people who want a cloud model without setting up a provider account.
Under the hood
A real model on your machine. Measured, not promised.
Offline mode runs Gemma 4 through llama.cpp on your own computer, on Apple’s GPU (Metal) on a Mac. It picks a model size that fits the memory you have free, and checks every model file against a pinned checksum before it runs.
- Reads your prompt
- 1,055 tokens/s
- How fast it takes in a long conversation or document before answering.
- Writes the answer
- 78 tokens/s
- Faster than you read. The first word arrives in under half a second.
- Starts up
- 4.2 s
- From a cold start to ready, loading a 3.2 GB model.
Measured on an Apple M2 Pro with 16 GB, Gemma 4 E2B, 8,192 tokens of context, 4 October 2026. Speeds vary with the computer and what else is running. We are measuring 8 GB Macs and Windows laptops next and will publish those too.
Asks before it acts
Nothing leaves without your yes.
Pivra Desk sorts every action by what it could do. The more it could change, the more it asks of you.
Reading and searching
AutomaticRuns on its own. Looking things up never needs a click.
Sending, publishing, paying, changing
Asks youWaits for your approval on a card that shows exactly what will happen.
Money, deletes and deploys
Touch ID or phraseCritical. Needs Touch ID on a Mac, or a typed phrase.
Want stricter limits? Write your own rules, and read them back any time. Security and privacy, in detail
Invoices
wants to send an email
- To
- accounts@northwind.example
- Subject
- Invoice 1042 is now 14 days overdue
- Message
- Hi Sam, a friendly reminder that invoice 1042 for $1,240 was due on 12 September. A copy is attached…
Nothing is sent until you approve.
An honest comparison
Pivra Desk or a cloud agent?
Both are useful. Here is where each one is the better choice.
| Feature |  Pivra Desk | Cloud agentshosted on a provider’s servers |
|---|---|---|
| Where it runs | ||
| Where it runs | Better: Your own Mac or Windows PC | The provider’s servers |
| Privacy | ||
| Privacy | Better: Runs on your machine. With a local model or your own key, nothing goes through Pivra | Your work is handled in their cloud |
| Model choice | ||
| Model choice | Better: On-device, Anthropic, OpenAI-compatible or local servers | The provider’s own models |
| Price | ||
| Price | Better: Free plan. Plus is US$6 a month | Usually a pricier subscription |
| Rules and approvals | ||
| Rules and approvals | Better: Your rules. Approve every send, payment or change | Mostly set by the provider |
| Works with your computer off | ||
| Works with your computer off | No. Runs while your computer is on | Better: Yes |
| Phone app | ||
| Phone app | No. Approvals from your own Slack or Teams bot | Better: Yes |
| Ready-made app catalog | ||
| Ready-made app catalog | MCP servers, Google Calendar, GitHub; Gmail with your own Google app | Better: Broader |
Need an agent that runs with your laptop closed or from your phone? A cloud agent is the better pick today.
Pricing
Start free. Upgrade when your agents earn it.
Free is free for good: one agent, a model on your computer or your own key, no card. Plus is US$6 (A$9) a month for as many agents as you like, one-click Google and GitHub, and the morning brief. Plus + Credits, coming soon, adds cloud model credits so you need no key at all.
Included in Pivra Pro and Business: every member of a Pro or Business workspace gets Desk Plus.
Free
One agent, your model, your computer. No card, no clock.
US$0per month
- 1 agent
- On-device model, or your own model key
- Files, routines and approvals
Plus
For people who hand their agents real work.
US$6per month
- Unlimited agents
- One-click Google and GitHub sign-in
- The morning brief
- Your own key or an on-device model
Plus + CreditsComing soon
Plus, with a cloud model ready to go. Nothing to set up.
US$15per month
- Everything in Plus
- Monthly cloud model credits
- No model key needed
Paid plans are not on sale yet. You are never locked out of your own data: if a payment lapses, paid features keep working through a grace period, then turn off. Your agents, files and history stay on your computer.
Join the waitlist
One email when paid plans open. The free plan works today, so you can start now and upgrade later.
FAQ
Questions, answered plainly.
Step-by-step guides are in the help centre: install, your first agent, choosing a model, approvals and rules, plans and troubleshooting. All Desk guides
Does it keep working when my computer is off?
No. Pivra Desk runs on your computer. Routines and follow-ups run while the app is open and the computer is on. If you need an agent that works with your laptop closed, a cloud agent is the better fit; Pivra Cloud is coming as an opt-in.
What does it do without asking?
Reading and searching. Anything that sends, publishes, pays or changes something waits for your approval on a card that shows exactly what will happen. Critical actions, like money, deletes and deploys, need Touch ID on a Mac or a typed phrase. You can write your own rules on top.
Which models can I use?
Offline mode: a built-in local model (Gemma 4 or a small Qwen) that runs on your computer with no key and no account; it suits reading, summaries and short tasks. Or your own key: Anthropic, OpenAI, OpenRouter, or any OpenAI-compatible endpoint, including local servers like Ollama, LM Studio and vLLM. Long, multi-step work is better with a larger model.
Does my data go through Pivra?
Not when you use a local model or your own key. Requests go from your computer to the model you chose, and credentials are sealed on your machine. Signing in to a plan contacts pivra.ai once to fetch a signed entitlement; app analytics are off unless you opt in. The security page lists every data flow.
Can it send email?
It drafts email and waits for your approval. Pivra’s built-in Google sign-in asks only for your calendar (read only) and your account email, so sending through Gmail needs your own Google sign-in app for now; without one, approved emails are saved as drafts for you to send.
Which Macs are supported?
Macs with Apple silicon. The Mac build does not run on Intel Macs. Offline mode works best with 16 GB of memory; the app picks a model size that fits what is free.
Windows showed a SmartScreen warning. Is that expected?
It can be. Pivra Desk is a new app, so Windows may show a SmartScreen notice the first time you open the installer. Choose More info, then Run anyway. The installer is signed, and the notice fades as more people install the app.
Is there a phone app?
No. If you connect your own Slack or Microsoft Teams bot, approval cards are sent there with buttons, so you can answer from your phone.
How much does it cost?
Free is $0 with one agent, an on-device model or your own model key, files, routines and approvals. Plus is US$6 (A$9) a month and adds unlimited agents, one-click Google and GitHub sign-in, and the morning brief. Plus + Credits, with cloud model credits so you need no key, is coming soon. Desk Plus is included for members of Pivra Pro and Business workspaces.
What happens if a payment fails or I cancel?
You are never locked out of your own data. Paid features keep working through a grace period, then turn off, and Pivra Desk carries on as the free plan. Your agents, files and history stay on your computer.
Put an agent on your desk.
Free to start. Your computer, your model, your approvals.
Download for Macv0.2.15 · Apple silicon · 150 MB
Download for Windowsv0.2.15 · Windows · 138 MB
