Skip to content
Docs
HomepageDemo
Overview
Getting started
QuickstartChoose an installationWhat is Metis?Accounts and initial setupConnect your first providerYour first taskSign inInstall on LinuxInstall on macOSInstall on Windows
Chat & context
Navigation & chatsCompose messagesResponses & tool callsAnswer questionsApprove actionsSearch & quick actions
Workspace
Agent overviewCanvasPlansMemoryFilesTerminalBrowserDesktopsServer monitorArrange the workspaceExport workspaces
Projects & teams
Create a projectProject overviewChat visibilityProject picture, color, and iconProject instructionsProject memoryProject skillsProject filesProject notesAgent model defaultLet agents manage the teamMembers & invitationsAgent teamsTeam presetsTeam overview
Notes
Notes & scratchpad
Agent Hub
SkillsConnections / MCPsCustom modes & rulesGlobal agent rules
Settings
GeneralModels — ConnectionsAgent — Runtime & memoryDevices — Remote clientsAdmin / ChatsUpdatesSearch settingsAttachments and file sizeSubagent modelToken compressionPreview compressionSounds and notificationsNotification deliverySet up voice inputChoose a microphoneRecording and streamingDictionaryConfigure the browser previewManage website dataWebsite and source code
Models & providers
AgentDeep ResearchPlanAskGauntletCursorOpenAIAnthropicGoogle GeminixAI / GrokOpenRouterOllama / LocalOpenAI-compatibleOpenAI CodexClaude CodeGoogle AntigravityGrok BuildOpenCodeModel options
Account & sharing
ProfileNotificationsUsage & costsShare chatsPublic shares
Guides & operations
Charts, graphs & mediaAutomationsOperate your installationTroubleshootingSet up a complete projectWork on a connected PCResearch and produce a reportGlossary and scopes
Metis AI
Docs/Projects & teams

Projects & teams

Agent teams

Agent teams contain named agents with their own roles, instructions, and conversations. A role describes responsibility; it does not grant additional technical permissions.

1 min readUpdated: October 2026
An agent-oriented project with three sample agents. Captured in an isolated Metis test instance with fictional sample data (October 2026).
An agent-oriented project with three sample agents

An agent-oriented project with three sample agents. Captured in an isolated Metis test instance with fictional sample data (October 2026).

Step by step

  1. 01

    Open an agent project and add a teammate with New agent.

  2. 02

    Define a name, role, System prompt, and optional Supervising agent.

  3. 03

    Choose the model in the agent's chat or through the project model default.

  4. 04

    Use Team activity to track assigned, active, and completed tasks.

Example prompt

Coordinate this project. Have the researcher clarify requirements and the tester independently verify the results against the acceptance criteria.

Your team

Requires an agent project.

  • Agent list
  • Pinned chats
  • Empty team
  • Starter team

New/Edit agent

Requires an agent project.

  • Name
  • Role
  • System prompt
  • Avatar color
  • Supervising agent

Agent actions

Requires an agent project.

  • Pin
  • Rename
  • Edit agent
  • Logs
  • Archive

Show archived agents

Requires an agent project.

  • View archived agents
  • Archive confirmation

Team activity

Requires an agent project.

  • Assignments
  • Status
  • Stop task
  • Retry

Good to know

  • Archiving preserves history and ends the affected agent's active work.
  • Stop task and Retry apply to a specific assignment.
  • Automatic team changes require the corresponding project permission.

Troubleshooting

If a teammate is busy, check Team activity and the queue before assigning the same task again.

Troubleshooting guide

Related articles

Create a projectProject overviewChat visibilityProject picture, color, and icon
PreviousMembers & invitationsNextTeam presets
Back to homepageReport an issue

On this page

Step by stepYour teamNew/Edit agentAgent actionsShow archived agentsTeam activityGood to knowTroubleshooting
Back to top ↑
Documentation
Overview
Getting started
QuickstartChoose an installationWhat is Metis?Accounts and initial setupConnect your first providerYour first taskSign inInstall on LinuxInstall on macOSInstall on Windows
Chat & context
Navigation & chatsCompose messagesResponses & tool callsAnswer questionsApprove actionsSearch & quick actions
Workspace
Agent overviewCanvasPlansMemoryFilesTerminalBrowserDesktopsServer monitorArrange the workspaceExport workspaces
Projects & teams
Create a projectProject overviewChat visibilityProject picture, color, and iconProject instructionsProject memoryProject skillsProject filesProject notesAgent model defaultLet agents manage the teamMembers & invitationsAgent teamsTeam presetsTeam overview
Notes
Notes & scratchpad
Agent Hub
SkillsConnections / MCPsCustom modes & rulesGlobal agent rules
Settings
GeneralModels — ConnectionsAgent — Runtime & memoryDevices — Remote clientsAdmin / ChatsUpdatesSearch settingsAttachments and file sizeSubagent modelToken compressionPreview compressionSounds and notificationsNotification deliverySet up voice inputChoose a microphoneRecording and streamingDictionaryConfigure the browser previewManage website dataWebsite and source code
Models & providers
AgentDeep ResearchPlanAskGauntletCursorOpenAIAnthropicGoogle GeminixAI / GrokOpenRouterOllama / LocalOpenAI-compatibleOpenAI CodexClaude CodeGoogle AntigravityGrok BuildOpenCodeModel options
Account & sharing
ProfileNotificationsUsage & costsShare chatsPublic shares
Guides & operations
Charts, graphs & mediaAutomationsOperate your installationTroubleshootingSet up a complete projectWork on a connected PCResearch and produce a reportGlossary and scopes

Popular starting points

Getting startedQuickstartGo from installation to your first verifiable task: set up Metis, connect a model, and start with a small request.Getting startedChoose an installationNative installation is recommended for Linux, macOS, and Windows. Install Metis on the computer or server that will run it, then pGetting startedWhat is Metis?Metis is your self-hosted workspace for AI agents. Conversations, files, browser, tools, and persistent context stay together. YouGetting startedAccounts and initial setupOn first launch, you set up the instance with an administrator account. The single-use operator token confirms your authority to mGetting startedConnect your first providerMetis needs model access to generate responses and run agent tasks. Setup displays authentication methods supported by the selecteGetting startedYour first taskCheck your setup with a small task whose result you can assess directly. You can then add files, browser access, or project contexGetting startedSign inSign in with an account on the relevant Metis instance. Your displayed profile name may differ from your login username.
↑ ↓ select · Enter openEsc close