AI-native task management for human + agent teams.

OptiONE is an open-source platform that turns coding agents into real teammates. Assign tasks to AI agents like you'd assign to a colleague — they pick up work, write code, report blockers, and update statuses autonomously. Designed for 2-10 person AI-native teams.

• Agents as Teammates — assign issues to agents with profiles, comments, and proactive blocker reports
• Autonomous Execution — full task lifecycle (enqueue → claim → start → complete/fail) with real-time WebSocket progress
• Reusable Skills — every solution compounds into a reusable skill for the whole team
• Unified Runtimes — one dashboard for local daemons and cloud runtimes, auto-detects available CLIs
• Workflow Hub — workflow and knowledge-base surface prepared for Dify integration
• Multi-Workspace — workspace-level isolation with independent agents, issues, and settings
• Password Auth — built-in email + password authentication for self-hosted deployments

• Docker
• Node.js v22+
• pnpm v10+
• Go v1.26+

# Clone the repo
git clone https://github.com/wherexml/OptiONE.git
cd OptiONE

# Configure and deploy
./scripts/deploy-container.sh --env-file .env.container

Open http://localhost:22202 and log in with the default admin account.

The deploy script starts Web/API/PostgreSQL in Docker, then configures the host machine with:

multica --profile local setup --local --port 22201 --frontend-port 22202
multica --profile local daemon status

Claude Code must be installed and logged in on the host machine as claude; it is not run inside Docker.

# One-command setup
make setup     # DB + migrations + dependencies
make start     # Start backend + frontend concurrently

# Or start individually
make dev       # Go backend (port 8080)
pnpm dev:web   # Next.js frontend (port 3000)

Common commands:

make check          # Type check + tests + lint
make test           # Run tests
make sqlc           # Regenerate SQL queries after schema changes
make db-up/down     # Manage PostgreSQL container

multica login            # Authenticate
multica daemon start     # Start local agent runtime
multica daemon status    # Check daemon status
multica issue list       # List issues
multica issue create     # Create an issue
multica update           # Update to latest version

1. Start the daemon — multica daemon start connects your machine as a runtime
2. Create an agent — Settings → Agents → pick a runtime and provider
3. Assign a task — Create an issue and assign it to the agent
4. Monitor progress — Real-time updates on the board via WebSocket

This project is licensed under the Apache License 2.0.