The agent runtime
that asks before it acts.

GnamiAI is a security-first AI agent runtime that runs in your browser. It gives your agent granular permissions, pauses destructive actions for human approval, and lets you compose specialized subagents, skills, long-term memory, and scheduled runs — without installing anything locally.

The dashboard, the CLI, and every existing feature are free — bring your own provider key (OpenAI, Anthropic, OpenRouter, Augure, Ollama) and you're billed by them at their rates, never by us. Pro is an optional $19/month tier with a 3-day free trial that adds Multi-Device Sync (encrypted chat transcripts shared between web and CLI), Extended Memory (full RAG over your documents), and Proactive Mode (schedules queue planned actions for your review). You only need Pro if you want one of those three things.

Click Start 3-day trial in Settings → Account, enter a card at the hosted checkout, and you get full Pro access for three days. We don't charge until day 4. Cancel any time before then from Settings → Manage subscription and you walk away at $0 — your account drops back to the free plan and any synced transcripts stay encrypted on the server until you delete them or the FK cascade fires on workspace deletion. After day 4, $19/mo USD ($24 CAD where the processor serves a Canadian price); cancel any time and you keep Pro through the end of the period you paid for.

Three things, on top of the free plan: (1) Multi-Device Sync — chat transcripts encrypted at rest with AES-256-GCM and synced between web and CLI; (2) Extended Memory — full RAG over documents you upload (chunked, embedded with OpenAI's text-embedding-3-small, retrieved at every turn); (3) Proactive Mode — flag a schedule as proactive and the agent's planned actions are queued in /proposals for your review instead of running silently.

OpenAI, Anthropic, OpenRouter (access to most open and closed models), Augure (Canadian-sovereign frontier models — Ossington and Tofino, on Canadian-owned infrastructure, compliant with Quebec Law 25 and federal privacy law), and Ollama (self-hosted). You can switch providers per turn and select models from each provider's catalog.

Yes, encrypted at rest with AES-256-GCM using a server-held key. A database dump alone does not leak your credentials. You can disconnect any provider from Settings and the row is deleted immediately.

No. Chat transcripts live in your browser's localStorage. The server forwards each turn to your chosen provider and does not retain prompt or response bodies. See the Privacy page for the full data map.

Yes — Ollama is a first-class provider and your models stay on your machine. Because the hosted GnamiAI server runs on Vercel, it needs to reach your Ollama instance over the network; the simplest way is a tunnel (e.g. Cloudflare Tunnel, ngrok) that exposes your local ollama serve at a public URL. Inference still happens locally on your hardware — the tunnel only carries the request. SSRF guards block private-network and loopback targets, which is why a raw http://localhost:11434 won't work on the hosted build.

A skill is a plain SKILL.md file that teaches the agent how to do something specific (write changelogs, draft release notes, generate conventional commits). A subagent is a named specialization with its own system prompt and model preference, pinned into chat with /agent <name>.

It can create subagents, install skills, and remember facts when you ask it to, via structured gnami-action JSON blocks. Destructive operations pause for an approval in the UI before running.