What is Gamut

An overview of Gamut, the platform for building and running personal AI agents in secure containers.

Gamut is a platform for building and running AI agents. You create agents, give them instructions, connect them to your accounts, and let them work autonomously in the background -- inside secure, containerized sandboxes.

How it works

Each agent you create in Gamut runs inside its own isolated container - a virtual computer it operates within. Inside that container, the agent can write and execute scripts, build agentic app, and do work using APIs, MCPs and your browser.

You interact with agents through a chat interface. You can send messages, ask questions, assign tasks, and watch the agent work in real time. Agents remember context across sessions, learn your preferences over time, and can be scheduled to run tasks on their own (at a scheduled time, or on a trigger).

When you give your agent access to your accounts / MCPs - they agent never gets the API keys. These requests always route through a proxy - so the agent can't leak your keys, and you get to decide which requests can go through and which require your approval.

Key capabilities

Containerized execution

Every agent runs in its own sandboxed container. The agent can execute code, install packages, read and write files, and run shell commands -- all without direct access to your host machine. This keeps your system secure while giving agents the freedom to get work done. The agent can't access your computer unless you give it specific access to it.

Each agent runs in its own locked-down sandbox — free to work inside, but it can't reach your machine.

Connected accounts

Gamut integrates with dozens of external services through OAuth -- Gmail, Slack, GitHub, Linear, Salesforce, Google Drive, and many more. You connect an account once, and any agent you authorize can use it. API calls are proxied outside the container, so agents never see your OAuth tokens. You get an audit trail of every action taken on your behalf.

Requests route through a proxy that enforces your policy. The OAuth token is attached after the proxy — the agent never sees it.

Browser automation

When no API is available, agents can open a web browser inside their container to interact with websites directly. You can watch the browser session in real time, and the agent can ask you for input when it encounters CAPTCHAs or login screens.

Agents drive a real browser inside the container — you watch every click in real time.

The agent can also use your browser (Chrome) directly -- letting it use your logged in accounts and bypassing bot detection.

Scheduled tasks and triggers

Agents can schedule recurring or one-time tasks using cron expressions or specific dates. You can also set up webhook triggers that start an agent session when an external event occurs. This lets agents serve you autonomously in the background without manual prompting.

Triggers wake an agent automatically — on a schedule, a new email, or the end of a meeting.

Dashboards and artifacts

Agents can build interactive dashboards -- small web apps rendered inside Gamut -- to surface information, charts, or controls. Agents can also deliver files and other artifacts directly to you during a conversation.

Agents assemble live dashboards — charts, metrics, and controls — right inside Gamut.

Multi-agent orchestration

Agents can discover, create, and invoke other agents in the same workspace. This lets you decompose complex workflows across specialized agents that collaborate to complete a task.

Agents discover, create, and invoke each other — decomposing a task across specialized collaborators.

Skillsets

As agents develop reusable capabilities, you can package them into skillsets -- shared skill libraries backed by Git repositories. Install a skillset to give any agent instant access to a curated set of skills, and publish your own to share with your team.

Package skills into a shared skillset — publish once, and any agent can install it.

Chat integration

You don't have to stay in the Gamut app to talk to your agents. Connect them to the messaging tools you already use -- iMessage, Telegram, and Slack -- and message an agent like you would a teammate. Send a task from your phone, ask a follow-up question, or get a heads-up the moment a scheduled run finishes or a trigger fires.

Agents reply in the same thread, keep the full conversation context across channels, and can reach out to you proactively -- so your agents are always a message away.

Chat with your agents from the apps you already use — message in, reply back, context kept across channels.

Deployment options

Gamut runs in two modes:

Desktop app -- Download for Mac or Windows and run locally. The desktop app bundles everything and manages containers through Docker Desktop, OrbStack, or Podman.
Web app / server -- Run Gamut as a Docker container or from source and access it through your browser. Supports multi-user auth mode with role-based access control for team deployments.

Next steps

Quickstart -- Create your first agent and start a conversation.
Core Concepts -- Understand the key abstractions: agents, sessions, containers, tools, and policies.