Who it is forAn operator who wants Franco on a Linux server, isolated from their laptop.
The problemInstalling Python, Chromium and the agent CLI by hand on a server is fiddly and easy to get wrong.
The outcomeFranco running in Docker with your data folder, .env and config mounted, and its dashboard reachable.
What you need first
- Python 3.11 or newer
- Claude Code logged in on a Pro or Max plan, or an opt-in Codex runtime on a ChatGPT plan
- A mailbox to send from (Google Workspace recommended) and email verifier keys
- Chromium, installed with franco install, for LinkedIn and JavaScript-heavy sites
Steps
- Run
docker pull ghcr.io/gortexai/franco:latest - Put your settings in Franco.local.yaml and your keys in .env
- Start it with
docker compose up -d - Optionally verify the image with
gh attestation verify oci://ghcr.io/gortexai/franco:latest --owner GortexAI - Open the dashboard and keep new campaigns in preview until you have read the first emails
Prompt for your agent
Deploy GortexAI/franco with the published ghcr.io image and docker compose on <server>, mount ./data, .env and my config, verify the image attestation, and confirm the dashboard loads.
Caveat. This card is written from the GortexAI/franco README, not from a test run by Deduped. Before you start, make sure you have Python 3.11 or newer. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for GortexAI/franco and "Run Franco from the published container image"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer