How can we help?
Write to us - a real person reads every message and answers within a business day. If you'd rather look first, the FAQ covers the common questions.
Frequently asked
What is Convira?
Convira is a desktop AI agent that can research, organize files, use a visible browser, and create or edit Word, Excel, PowerPoint, and PDF documents. You can watch the work, approve sensitive actions, and choose where the AI processing runs.
What's the difference between Local AI, Cloud, and Private Box?
Local AI runs an Ollama-compatible model on your machine - your context, prompts, memory, and files stay on the device. The one exception is a billed tool you invoke (web and X research, image and video generation, connector actions): it needs managed provider keys we hold, so that single call runs on Convira when you're online and is unavailable offline. Best for sensitive work and offline use.
Cloud uses hosted AI models with no local model setup. Convira processes the request and forwards the necessary prompt and context to the selected model provider, but does not retain the run content in its database. The authoritative run record stays on your device.
Private Box is a strong machine you control on your LAN. The desktop talks to it directly - no cloud hop in the run itself, though Convira licenses the box with a signed credential your desktop renews about once a day, so it needs an active subscription and periodic connectivity. Good for bigger models that don't fit on a laptop without leaving your network.
Which Macs are supported?
Apple Silicon only - M1, M2, M3, M4 - on macOS 12 Monterey or newer. Intel Macs aren't supported. The local-model runtime depends on the Apple Silicon ML stack and we don't ship a universal binary.
Which Windows versions are supported?
Windows 10 and Windows 11, 64-bit (x64). One installer covers both. No Windows ARM build - the x64 installer may run under emulation, but we don't test it and local models would be slow there, so we don't recommend it.
Which Linux distros are supported?
Ubuntu 22.04+, Debian 12+, and Fedora 38+ on x86_64. The .deb installs on Debian and Ubuntu; the .tar.gz unpacks and runs on any other distro. No ARM, no RPM, no Flatpak/Snap in v1.
How does auto-update work?
Convira checks for a new version on launch and every so often while the app is open. Nothing downloads until you ask it to. On macOS and Windows the update installs when you restart or quit, and those builds also use the operating system's code-signing checks. On Linux the app tells you a new version exists and links you to the download. Update traffic is skipped when Convira's egress policy blocks it.
Where does my data go in Cloud mode?
Convira processes the request and forwards the necessary prompt and context to the selected AI model provider. Run content is not written to Convira's database; the authoritative session record remains on your device. Operational metadata such as status, model, tools, token use, and credit use may be retained. See the Security and Privacy pages for the full data-path explanation.
What models can I run with Local AI?
Convira supports its curated local catalog and compatible Ollama models. The model picker checks your available hardware and shows which choices fit, so you do not need to compare model sizes by hand.
What models can I run on a Private Box?
The same catalog as Local AI plus much larger models - from 119B up to trillion-parameter mixture-of-experts models - that no laptop can hold. Because the box has memory a laptop doesn't, Convira allows bigger models there.
Can my whole team use one Private Box?
Yes - a Private Box is shared across your workspace. The desktop that paired it seals the box credential to each member's device key (X25519), so Convira never sees it in plaintext. Each member's desktop unseals it locally to reach the box.
Do I need to be online?
Cloud and Private Box need network reachability. Local AI runs offline once you've pulled the models - for up to 24 hours between check-ins. There's a one-click Offline Mode toggle in the app footer. It blocks all outgoing traffic except your machine's own local services and Convira's sign-in and licensing endpoints, and cuts off in-flight requests the moment you flip it.
What hardware do I need?
Minimum: 8 GB RAM and about 4 GB of disk - the app bundles its document engine and small on-device helper models.
Recommended for local AI: 16 GB+ RAM. Models take from about 2.5 GB to over 80 GB of disk each; most mainstream picks are 5-25 GB. Apple Silicon with 16 GB of unified memory runs 9B-class models comfortably; 32B-class models need about 32 GB. The model picker only offers what fits your machine.
How much does it cost?
Plans differ by included cloud credits, collaboration features, and Private Box access. See the Pricing page for the current plans and billing options.
How do I uninstall?
macOS: drag Convira from Applications to the Trash.
Windows: Settings → Apps → Convira → Uninstall.
Linux .deb: sudo apt remove convira-desktop. Linux tarball: delete the unpacked folder.
My install failed / model won't load / Private Box won't pair - help?
Use the form on this page - the message field lists what we need. The one thing to copy exactly is the error text from the wizard, since that usually points straight at the cause.