Oduflow

An AI-first Odoo development and CI tool, powered by reusable database templates. Oduflow provisions isolated, ephemeral Odoo environments on Docker — one per git branch — and exposes them to AI coding agents via MCP, creating a closed feedback loop that enables fully autonomous Odoo development.

Beyond Vibe Coding: Spec-Driven Development

Vibe coding — chatting with an AI and eyeballing the output — was the first wave. It works for prototypes, but breaks down on real ERP systems where a module must install cleanly, pass tests, and work against production data.

Spec-Driven Development (SDD) is the next step: you write a precise specification of what the module should do, and the AI agent autonomously implements how — because it has a closed feedback loop with the running system:

┌──────────────────────────────────────────────────────┐
│                    AI Agent                          │
│          (Cursor, Cline, Amp, Claude, …)             │
└──────┬──────────────────────────────▲────────────────┘
       │ 1. Read spec                 │ 5. Read errors,
       │ 2. Write code                │    fix code,
       │ 3. Install module via MCP    │    retry
       │ 4. Click-test UI via         │
       │    Playwright MCP            │
┌──────▼──────────────────────────────┴────────────────┐
│               Oduflow (MCP Server)                   │
│  • install_odoo_modules → traceback or success       │
│  • run_odoo_tests → test pass/fail with details      │
│  • get_environment_logs → runtime errors             │
│  • upgrade_odoo_modules → upgrade output             │
├──────────────────────────────────────────────────────┤
│            + Playwright MCP / other tools            │
│  • Navigate Odoo UI, click buttons, fill forms       │
│  • Verify business logic end-to-end                  │
│  • Validate acceptance criteria from the spec        │
└──────────────────────────────────────────────────────┘

The agent writes code, installs the module, reads the traceback, fixes the error, retries — and when it installs cleanly, it can open the browser via Playwright MCP to click through the UI, verify business flows, and validate acceptance criteria — all without human intervention. connect_as_user closes the last gap: it mints a passwordless Odoo session and hands back the cookie, so Playwright lands past /web/login as any role (admin, sales manager, portal) — no credentials to type, no login form.

Quick Start

1. Install

pip install oduflow

2. Start the MCP server

oduflow

That's it. On first launch, Oduflow automatically creates a default config and initializes shared infrastructure (Docker network, PostgreSQL, team directories).

The generated config is written to /etc/oduflow/oduflow.toml when writable, otherwise to ~/.oduflow/conf/oduflow.toml. Fresh configs include generated secrets for HTTP access: [team.1].auth_token for MCP clients and [team.1].ui_password for the Web Dashboard. Both values are also printed in the startup log.

By default, the server starts in stdio mode (for local MCP clients). For remote/multi-user deployments:

oduflow --transport http
oduflow -t http

3. Connect an MCP client

stdio (local) — add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "oduflow": {
      "command": "oduflow"
    }
  }
}

HTTP (remote) — point your MCP client to http://<host>:8000/mcp and send Authorization: Bearer <auth_token> using the token from oduflow.toml.

The Web Dashboard is available at http://<host>:8000/. Sign in as admin with the ui_password from oduflow.toml; this is separate from the MCP Bearer token.

Documentation

For full documentation, visit oduflow.dev or see the docs/ folder:

• Installation & Configuration
• Use Cases & Workflows
• Template Management
• Environment Management
• Coding Agent
• Auxiliary Services
• Extra Addons Repositories
• Web Dashboard & REST API
• MCP Tools Reference
• CLI Reference
• Traefik Routing (Auto-HTTPS)
• Multi-Instance Support
• Authentication & Security
• Running in Docker
• Internals
• Licensing

Telemetry

Oduflow collects anonymous usage telemetry (first startup and environment creation events) to understand adoption. Only the event name, version, and a random instance ID are sent — no personal data or environment details. To opt out, add disable_telemetry = true to the [server] section of your oduflow.toml. See the documentation for details.

Licensing

Oduflow is source-available under the Business Source License 1.1. Evaluation, educational, and other non-commercial use is free forever. Commercial use requires a paid license in one of three tiers — Individual (solo developers), Business (internal company use), or Integrator (Odoo service providers) — visit oduflow.dev. Each release converts to the open-source MPL 2.0 four years after publication.