MASMulti-agent workspace

MULTI-AGENT SYSTEM

Agents, skills and sandboxes,
composed into repeatable work

Create sessions, configure models, attach skills and run sandboxes in one workspace. The left menu is the whole product — set it up once, reuse it everywhere.

Read the docs5-minute quickstart
01

Capabilities

Six things, one entry point

  1. 01

    Agents

    Bind a role, prompts, tools and skills once; pick the agent in any session.

  2. 02

    Skills

    Package a workflow as a skill so the agent loads it on demand.

  3. 03

    MCP

    Connect external tools and data sources, managed centrally and composed per agent.

  4. 04

    Sandbox

    Every command runs in an isolated environment you can preview and discard.

  5. 05

    Exchange Space

    Inject secrets and files into the runtime without putting them in prompts.

  6. 06

    GitHub

    Repos, tokens and webhooks in one place, so agents can work on code directly.

02

Getting started

Three steps to your first session

  1. 1

    Configure a model

    Open LLM in the left menu, create one with your API key and model ID.

  2. 2

    Start a session

    Pick an agent and start chatting; the default config works too.

  3. 3

    Extend as needed

    Attach MCP servers, skills and tools, or run commands in a sandbox.