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/Chat & context

Chat & context

Compose messages

Use the composer to describe your task and choose context, model, mode, and execution permissions. These choices determine what the next task can access and which actions it can perform.

1 min readUpdated: October 2026
A chat with a saved response. Captured in an isolated Metis test instance with fictional sample data (October 2026).
A chat with a saved response

A chat with a saved response. Captured in an isolated Metis test instance with fictional sample data (October 2026).

Step by step

  1. 01

    Describe your goal, source material, and expected result in Message.

  2. 02

    Add files under Add, or use @ to select existing context.

  3. 03

    Check the model, agent mode, and Access before sending.

  4. 04

    Send the message. While a task is running, you can queue additional messages.

Example prompt

Review @Project plan for missing dependencies. Create a prioritized list and explain the first three items.

Message

  • Compose messages
  • Multiline input
  • Send
  • Dynamic sending status

Add → Files

  • Select files and images
  • Drag and drop
  • Upload progress
  • Remove attachments
  • Restored attachments

Add → Context / @

  • file
  • canvas
  • plan
  • note
  • browser
  • terminal
  • memory
  • chat
  • Category search
  • Remove references
  • Reference selected text

Slash commands

  • Choose commands in the composer
  • Keyboard selection
  • Commands available in your installation

Model picker

  • Provider groups
  • Search
  • Favorites
  • Custom model ID
  • Missing connection state

Agent mode

  • Choose a mode
  • Provider-specific availability

Access / Execution approvals

  • Different confirmation levels for file edits and commands
  • Approval scope

Message queue

  • Queue during execution
  • Reorder
  • Edit
  • Remove
  • Pending questions

Voice input

  • Record
  • Waveform
  • Stop
  • Transcribe
  • Cancel
  • Attachment status

Context and quota

  • Used context
  • Model maximum
  • Measured or estimated values
  • Provider quota

Stop and resume tasks

  • Stop agent
  • Resume
  • Dismiss
  • Interrupted execution

Find in chat

  • Search the open chat
  • Previous or next match
  • Close

Good to know

  • A reference links existing context to the task. An upload provides an additional file.
  • Selecting a suggested reply fills the composer; Send submits it.
  • Available model options depend on the detected connection and model.

Troubleshooting

If Send is unavailable, check pending uploads, unanswered questions, and the provider connection.

Troubleshooting guide

Related articles

Navigation & chatsResponses & tool callsAnswer questionsApprove actions
PreviousNavigation & chatsNextResponses & tool calls
Back to homepageReport an issue

On this page

Step by stepMessageAdd → FilesAdd → Context / @Slash commandsModel pickerAgent modeAccess / Execution approvalsMessage queueVoice inputContext and quotaStop and resume tasksFind in chatGood 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