Skip to main content
Start with a short outcome workflow, then use the canonical capability guide when you need all options and safeguards. An Agent can run on your computer as a Connected Agent or remotely as a Cloud Agent; Agent software is a separate choice. Availability can still vary by run path, Agent software, and current runtime state. Start with Core concepts if Project, Memory, Session, Skill, Vault, Connector, Channel, or AI Provider is new to you.

​
Everyday workflows

Give an Agent shared context

Save one reusable preference and verify it in a new Agent interaction.

Connect an app and verify its tools

Authorize an app and confirm its live tools before asking the Agent to act.

Share a Project with a teammate

Invite a Viewer, let them review access, and add the Project to an Agent.

Connect a messaging Channel

Connect a bot, link a Cloud Agent, pair one chat, and send a test message.

​
Capability guides

Projects and sharing

Organize Skills and Vault access, invite Viewers, and attach Projects to Agents.

Memories

Save durable context, search it, and remove outdated information.

Sessions

Sync, review, share, and export supported conversation history.

Skills

Manage Agent-authoritative files and Cloud-owned Project Skills safely.

Vaults and secrets

Store secrets, commit references, and resolve them only where needed.

Connectors and MCP

Connect apps and verify that an Agent can reach the available tools.

Channels

Connect a bot, link an Agent, and pair or unpair external chats.

AI Providers

Keep the local Connected Agent catalog separate from Cloud Agent controls.
For command discovery and version-specific flags, use the CLI command map and the --help output shipped with your installed CLI.
Last modified on August 2, 2026