crewkit
MarketplaceFeaturesPricingDocsGitHub
Sign InGet Started
crewkitInstallationQuickstartConfigurationTroubleshootingFAQ

Usage

TUICLIDashboardAnalytics

Collaborate

ArtifactsSession sharingBlueprintsAgent identitiesMCP server

Configure

AgentsSkillsRulesCommandsInheritancePlaybooksExperimentsHooksTeamWorkspaces

API Reference

API OverviewAuthenticationSessions APIResources APIOrganizations APIProjects APIPlaybooks APIExperiments API

CLI

Complete command reference for the crewkit CLI.

The crewkit CLI manages your AI coding sessions, team configuration, and project setup from the terminal.

crewkit              # Show status overview
crewkit code         # Start a coding session
crewkit auth login   # Connect to your account

Commands

crewkit code

Start a coding session with your team's agents.

crewkit code                          # Interactive TUI session
crewkit code --prompt "Fix the bug"   # Headless one-shot
crewkit code --continue               # Continue most recent session
crewkit code --resume                 # Pick a session to resume
crewkit code --resume <id>            # Resume specific session

Flags:

FlagDescription
--debugEnable debug logging (per-session log at .crewkit/debug-latest.log)
-v, --verboseShow detailed output (file lists, timing)
-p, --prompt <text>Run headless with a prompt
--output-format <fmt>Output format: text, json, stream-json (requires --prompt)
--timeout <secs>Max execution time for headless mode (default: 300)
-q, --quietSuppress progress output in headless mode
-c, --continueContinue most recent Claude session
-r, --resume [id]Resume a session by ID, or show picker
--fork-sessionFork the resumed session (new ID, existing context)
--sensitiveMark session as sensitive (excluded from cross-repo discovery)
--repo-id <id>Explicit repository ID (also: CREWKIT_REPOSITORY_ID env var)
-y, --yesSkip interactive prompts (for CI/CD)
--no-authSkip authentication (sessions will not be tracked)
--no-tuiSkip the crewkit TUI: run native claude in this terminal while crewkit observes (Unix-only; see crewkit sidecar)
--no-artifactsDisable artifact context injection into the session
--no-contextSkip injecting save-state recall context (personal + team digests)
--no-titleDisable terminal window title
--disable-lspDisable LSP server auto-start
--chromeUse Chrome for browser automation
--llm-gatewayEnable LLM gateway proxy
--llm-gateway-port <port>Gateway proxy port (default: ephemeral)
--dangerously-skip-permissionsSkip all permission prompts (CI/CD only — disables safety checks)

crewkit sidecar

Run native Claude Code while crewkit observes in the background (Unix-only — macOS and Linux). claude owns the terminal; crewkit tracks telemetry alongside it. Same as crewkit code --no-tui, as a dedicated command.

crewkit sidecar                       # Launch claude with a background observer
crewkit sidecar status                # Show observer state for this project
crewkit sidecar status --json         # Machine-readable state
crewkit sidecar stop                  # Stop the observer in this terminal
crewkit sidecar stop --all            # Stop every observer for this directory

crewkit init

Set up crewkit for the current project.

crewkit init                # Interactive setup
crewkit init --workspace    # Create a workspace (multi-repo) project
crewkit init --yes          # Non-interactive with defaults

crewkit auth

Manage authentication.

crewkit auth login    # Log in via device flow
crewkit auth logout   # Log out and clear tokens
crewkit auth status   # Show current auth status

crewkit org

Organization management.

crewkit org info                    # Show current org info
crewkit org info --org acme         # Show specific org
crewkit org update --name "Acme"    # Update org name
crewkit org delete --org acme       # Delete org (requires --force)

crewkit project

Project management.

crewkit project list                     # List projects
crewkit project create my-project        # Create project
crewkit project info                     # Show current project
crewkit project update --name "New Name" # Update project
crewkit project delete -p my-project     # Delete project

crewkit members

Team member management.

crewkit members list                           # List members
crewkit members invite user@example.com        # Invite (default: member role)
crewkit members invite user@example.com -r admin  # Invite as admin
crewkit members update user@example.com -r admin  # Change role
crewkit members remove user@example.com        # Remove member
crewkit members invitations                    # List pending invitations

crewkit resources

View and manage resources (agents, skills, commands, rules).

crewkit resources list                        # List all resources
crewkit resources list --type agent            # Filter by type
crewkit resources show rails-expert            # Show resource details
crewkit resources inspect rails-expert         # Inspect full config
crewkit resources import                      # Import local resources
crewkit resources import --dry-run             # Preview import

crewkit playbooks

Preview applicable playbooks.

crewkit playbooks list              # List playbooks
crewkit playbooks list --detail     # Show convention details
crewkit playbooks show <id>         # Show specific playbook

crewkit sessions

Browse, inspect, share, and report on sessions.

crewkit sessions list                            # Recent sessions (current project)
crewkit sessions list --all-projects             # Across the whole organization
crewkit sessions list --since 7d --user me       # Your sessions from the last week
crewkit sessions show <id>                       # Full detail (accepts short id prefix)
crewkit sessions report --week                   # Team digest: sessions, cost, top agents

Share a session — create, list, or revoke share links:

crewkit sessions share <id>                      # Org-visible link, expires in 7 days
crewkit sessions share <id> --access public      # Anyone with the link (requires admin)
crewkit sessions share <id> --level summary      # Levels: summary, transcript, full
crewkit sessions share <id> --expires 0          # Never expires
crewkit sessions share <id> --list               # List existing shares
crewkit sessions share <id> --revoke <share-id>  # Revoke a share

Import history — bring in local Claude Code JSONL transcripts:

crewkit sessions import                          # Import local Claude conversations
crewkit sessions import --since 2026-01-01       # Import recent only
crewkit sessions import --dry-run                # Preview what would import
crewkit sessions import <transcript-id>          # Import specific conversation

Most subcommands accept --json for piping.


crewkit blueprint

AI-powered project planning with epics and tasks.

crewkit blueprint create "Ship the billing revamp"  # Generate a blueprint from a goal
crewkit blueprint list                              # List blueprints for this project
crewkit blueprint show <id>                         # Epics and tasks
crewkit blueprint review                            # Review against the local codebase
crewkit blueprint tasks --status pending            # List tasks, filter by status
crewkit blueprint start <task-id>                   # Claim a task (sets in_progress)
crewkit blueprint complete <task-id>                # Mark a task completed
crewkit blueprint export                            # Export as a plan file to .claude/work/

crewkit save-state

Manage project save states (personal handoffs + team digests).

crewkit save-state ls               # List this project's save states
crewkit save-state show personal    # Show your handoff
crewkit save-state show team        # Show the most recent team digest
crewkit save-state rm <id>          # Delete a save state

crewkit experiments

A/B test agent changes.

crewkit experiments list                          # List experiments
crewkit experiments create rails-expert           # Create experiment
crewkit experiments show swift-amber-falcon       # Show details
crewkit experiments metrics swift-amber-falcon    # View metrics
crewkit experiments deploy swift-amber-falcon     # Deploy winner

crewkit lsp

Code intelligence server for Claude Code.

crewkit lsp install            # Install plugin (user-wide)
crewkit lsp install --project  # Install for current project
crewkit lsp uninstall          # Remove plugin
crewkit lsp status             # Check installation
crewkit lsp start              # Start LSP server (usually auto-started)

crewkit mcp

MCP server exposing crewkit's project memory to agents. Any MCP-capable agent can pull project context, conventions, prior work, active work, and blueprint state. Sessions launched by crewkit code register it automatically.

crewkit mcp serve                     # Start the stdio MCP server
crewkit mcp serve --org <id>          # Override organization detection
crewkit mcp serve --project <id>      # Override project detection

Utility commands

crewkit whoami                   # Show current user
crewkit update                   # Update crewkit
crewkit update --check           # Check for updates
crewkit feedback "message"       # Send feedback
crewkit completions zsh          # Generate shell completions (bash, zsh, fish, ...)

Global flags

FlagDescription
--no-colorDisable colors (also respects NO_COLOR env var)
--plainASCII-only output (no unicode symbols)
--debugEnable debug logging (per-session log at .crewkit/debug-latest.log)
--versionShow version
--helpShow help

Next steps

  • TUI interface
  • Configuration

TUI

The terminal interface that wraps Claude Code with real-time metrics.

Dashboard

Navigate the crewkit web dashboard to view sessions, analytics, and team settings.

On this page

Commandscrewkit codecrewkit sidecarcrewkit initcrewkit authcrewkit orgcrewkit projectcrewkit memberscrewkit resourcescrewkit playbookscrewkit sessionscrewkit blueprintcrewkit save-statecrewkit experimentscrewkit lspcrewkit mcpUtility commandsGlobal flagsNext steps
crewkit

crewkit is the institutional memory and governance layer for AI-assisted engineering: agents work as teammates, prior work is one search away, and every session is attributed to the exact agent version that ran it.

Product

  • Marketplace
  • Features
  • Pricing
  • Documentation

Resources

  • GitHub
  • Changelog
  • Report Issue
  • System Status

Company

  • About
  • Privacy
  • Terms

© 2026 Karibew Inc. All rights reserved.

Command Palette

Search conversations, projects, playbooks, and more