Analysis updated 2026-05-18
Send tens of thousands of personalized emails a day without one server becoming a bottleneck.
Segment customers by custom attributes and target each segment with different templates.
Let an AI agent like Claude trigger and manage email campaigns through MCP tools.
Track per-recipient delivery status and automatically retry failed sends.
| sepfazeli/campaignforge | 920linjerry-stack/capital-studio | adya84/ha-world-cup-2026 | |
|---|---|---|---|
| Stars | 16 | 16 | 16 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | easy | easy |
| Complexity | 4/5 | 3/5 | 2/5 |
| Audience | developer | researcher | general |
Figures from each repo's GitHub metadata at analysis time.
Requires Docker Compose plus Redis and PostgreSQL to run the full stack.
CampaignForge is a tool for sending large batches of personalized email campaigns, built on the Django web framework. It lets you group customers into segments based on any attribute you choose, build email templates that change per recipient, and send tens of thousands of emails a day by splitting the work across background workers instead of one process trying to send everything at once. It comes with a REST API for managing subscribers, segments, templates, and campaigns, triggering sends, and checking delivery statistics as they come in. It also exposes the same operations through something called an MCP server, which means an AI assistant like Claude can be connected to drive campaigns directly through conversation instead of clicking through a dashboard. Under the hood, when a campaign is sent, the system splits recipients into fixed size batches, defaulting to 500 people per batch, and hands each batch to a background worker process managed by Celery, using Redis as the queue that holds pending work. Each worker then sends its batch of emails out through an email provider, with automatic retries if a send fails temporarily. Because the work is split into small batches handled by separate workers, you can add more worker processes to send faster without any single process becoming a bottleneck. To try it, you copy an example environment file, start everything with Docker Compose, then run a database migration and create an admin user, after which the REST API and admin panel are available locally. The project also includes setup docs for running without Docker.
A Django based engine for sending large, personalized email campaigns in batches, with an API and AI agent access via MCP.
Mainly Python. The stack also includes Python, Django, Celery.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.