Shared control plane for AI coding agents — Claude Code, Cursor, Windsurf, and teammates sync tasks, persistent memory, decisions, and file locks through one MCP server. 12 consolidated tools (~15KB): task claim/release with resume packs, semantic memory search, lock policies & cost caps, approval workflows, automations with Slack/Discord alerts, live team console. Free tier: 2 agents, 100 tasks/mo. Setup: npx @doriku/cli setup
Overview
@doriku/cli
The CLI for Doriku — an MCP-native governance plane for multi-IDE coding agents. Set up MCP config and Claude Code hooks, then manage workflows, file-lock policies, and cost caps from the terminal.
Quick Start
npx @doriku/cli setup
That's it. Your MCP server config and Claude Code hooks are ready.
Recommended next workflow (AI-friendly):
- Register your agent
- Create a task
- Log progress
- Update task status/result
Recommended first-value goal (15 minutes):
- Connect MCP successfully (connection test passes)
- Create one real engineering task
- Generate one summary snapshot
- Invite one teammate to review the shared state
See docs for MCP/API contracts, first-value onboarding, and recipe examples:
Installation
# Run directly (no install needed)
npx @doriku/cli setup
# Or install globally
npm install -g @doriku/cli
doriku setup
Setup Flow
- Sign in at doriku.io/console and create an API key
- Run the setup command
- Enter your API key when prompted — done!
Non-Interactive Mode
npx @doriku/cli setup --token drk_live_your_key_here --yes
What It Does
| Step | Description |
|---|---|
| MCP Configuration | Writes .mcp.json with your Doriku server config (merges with existing servers) |
| Claude Code Hooks | Installs hooks in ~/.claude/settings.json for automatic task sync |
| Connection Test | Verifies your API key works against the Doriku API |
| Workflow Management | List, run, monitor, and cancel multi-step agent workflows |
| Lock Policies | Define and inspect file-lock policies to prevent agent conflicts |
| Cost Caps | View and set workspace-level daily token spend limits |
Doriku also exposes AI-friendly MCP/REST contracts (structured MCP errors, machine-readable REST error fields, and a core OpenAPI spec) to make agent retries and recovery easier.
Who This Is For
- Solo developers and teams using Claude Code, Cursor, or Windsurf in parallel
- Anyone who needs governance (file locks, cost caps, audit trails) across multi-IDE agents
- Teams that need approvals, auditability, and operational visibility across agent work
CLI Reference
Usage: doriku <command> [options]
Commands:
setup Configure MCP and Claude Code hooks
workflow <subcommand> Manage workflow definitions and runs
lock <subcommand> Manage file-lock policies
cost <subcommand> Manage workspace cost caps
Options:
--token <key> API key (drk_live_...)
--yes, -y Non-interactive mode (accept all defaults)
--skip-hooks Skip Claude Code hook installation
--skip-test Skip connection test
-d, --dir <path> Target directory for .mcp.json (default: cwd)
--api-url <url> API base URL (default: https://api.doriku.io)
--help, -h Show help
--version, -v Show version
Workflow Subcommands
doriku workflow list # List all workflow definitions
doriku workflow run <slug> # Start a workflow run
doriku workflow status <runId> # Show run status and step summary
doriku workflow logs <runId> # Show step-level timeline
doriku workflow cancel <runId> # Cancel an in-progress run
Lock Subcommands
doriku lock list # List all file-lock policies
doriku lock policy # Define a new policy (interactive)
Cost Subcommands
doriku cost status # Show current cost cap config and today's usage
doriku cost set # Set daily token cap (interactive)
Links
License
MIT
Server Config
{
"mcpServers": {
"doriku": {
"type": "http",
"url": "https://api.doriku.io/mcp",
"headers": {
"Authorization": "Bearer <YOUR_DORIKU_API_KEY>"
}
}
}
}