53 topics · 10 groups
Documentation
One page per topic, each one covering what it is for and how to use it. Search below looks inside every page, not just the titles.
Getting started
Chat
- Chat basics Type, send, read. The reply streams token by token and the cost strip under it fills in while it writes. Edit a message to fork the conversation from that point. The original stays…
- Choosing a model The picker above the input lists every available model with its price per million tokens and its context length.
- Files and images in chat Attach with the clip, or paste an image straight into the box.
- Long conversations When a thread approaches the model's context limit, older turns are compacted into a summary so the conversation can continue instead of failing.
- Prompt optimiser A separate area for building and refining prompts.
- Skills Reusable instruction files the AI can load when relevant, instead of you re-explaining a workflow every time.
- Memory and writing style Facts worth carrying between conversations: how you like code formatted, what stack you use, what you are working on, plus an optional writing-style profile so replies sound the way you want.
- Context stitching Pull relevant material from your own documents and past work into a conversation, so the model answers with your context rather than in general.
- Research mode For questions that need sources rather than an opinion.
- Voice Speak instead of typing, and have replies read aloud.
- Buddy An optional on-screen companion that reflects what the system is doing: working, waiting for approval, out of credit.
- Import from ChatGPT, Claude, Gemini Bring your existing conversations in. Export from the other service, upload the file here, preview what was found, then confirm. Parsing happens locally and is free , so you are no…
Compute
- Containers Containers → New container , pick a base image (Ubuntu 24.04, Debian 12, Alpine) and a name.
- Command approval Every command the AI wants to run appears in full and waits.
- Files A real file tree of the container. Browse, open in the editor, upload, download. Download a single file or a whole folder as an archive. Edits you make are immediately what the AI…
- Terminal A shell in the same container, available mid-task without stopping the agent.
- Network drive (SMB) Not available yet. The plan gate and the share builder exist and are tested, but nothing calls them, and the storage box this would mount from is not reachable from the network the…
- Public ports Start something listening in the container, then publish that port.
- Custom domains On Pro and above you can point your own domain at a published port.
- Outbound network Containers reach the internet through a controlled gateway rather than directly.
- Virtual machines Where a container is not enough (a different kernel, systemd, or Windows), a full VM can be created from an admin-defined template, within your quota.
- Desktop control For graphical work, a desktop session in its own section.
Agents
- /goal Type /goal and what you want, in plain language: /goal migrate this project to TypeScript and get the tests green The agent plans, works, verifies its own result, and keeps going until it is done or genuinely stuck.
- /ultracode Where /goal is one model working through a task, /ultracode splits the work across several that check each other before anything reaches you.
- Jobs and logs Every long-running piece of work (an agent run, an import, a snapshot) appears under Jobs with its state and its log.
- Scheduled tasks Give an agent a job and a time: a nightly build, a daily check, a weekly summary.
- Invisible automation Standing permissions for routine actions, with an approval queue for anything outside them, plus a digest of what was done.
Browser
Research and security
- Deep research A longer, structured version of research mode for questions where you want a report rather than an answer.
- Legal research A corpus of primary legal sources that a model searches and quotes from directly, instead of recalling what it once read about the law.
- Security scan A real penetration test against a site you have proved you own , run by a model in a loop: it forms a hypothesis, tests it, reads what came back, and goes again.
Money
- Cost per answer Under each reply: input tokens, cached tokens, output tokens, and the price, updating while it streams.
- Credit and top-ups Credit is prepaid . You name an amount in CHF and pay through the MoonPay checkout, which settles into a self-custodied USDC wallet; a card works there, through MoonPay's onramp. A…
- Wallets, and how to get USDC The fast way to top up is to pay from your own wallet: it settles in seconds and nobody checks your ID, because you are simply sending money you already hold.
- Spend limits Set a hard limit per account, per chat or per agent run.
- Budget governor Watches spending as it happens and can downgrade to a cheaper model when a run is burning faster than expected, rather than stopping outright.
- Plans A plan buys hardware , not tokens. Plan Per month Cores RAM Disk Running Agent run Ports Free CHF 0 1 2 GB 2 GB 2 60 min — Mini CHF 4.50 2 6 GB 5 GB 3 4 h 1 Pro CHF 13.50 4 12 GB 1…
Keys and privacy
- Two-factor authentication and passkeys There is no email address on your account, which means there is no password reset and no "recover by email" path for an attacker either.
- Secrets vault Store credentials the AI needs (a deploy token, a database password) encrypted, and attach them to a chat when needed.
- Your own API key Already paying a provider? Add your key and that usage goes to your account there instead of your ZeroLog credit.
- Your own vendor subscription Sign a CLI in with your own account and it runs on your subscription instead of your credit here.
- Anonymous chats Switch a chat to anonym and it is encrypted in your browser before it is sent.
- Zero data retention Being rebuilt, do not rely on it today. The setting exists and a chat that touches vault credentials still flips it, but the flag it sends is one specific provider's field, and the…
Media
Connect
- Connectors Optional links to outside services (for example an image service or a Google account) enabled per account.
- Push notifications Get told when a long run finishes or an approval is waiting, instead of watching a tab.
- Webhooks Let an outside system trigger work here, or be told when something finished.
- Sharing a container Not available yet. The three roles, the revocation path and the plan gate are implemented and tested, with 26 assertions behind them, but no screen calls into them. What it will do…
- Android app Set aside for now. The Android package builds and signs, and Settings, Devices lists your signed-in devices and lets you revoke any of them. What is missing is the button on that p…
- Claude Code and other CLIs The vendor command-line tools are installed in every container from npm at pinned versions and are not modified: @anthropic-ai/claude-code , @openai/codex and @google/gemini-cli .