by Torvexis LLC
Build and run AI-powered workflows on your own infrastructure. Visual drag-and-drop builder, real-time chat execution, and a modular architecture that keeps your data where it belongs.
A complete platform for designing, running, and managing automated workflows with AI at the core.
Drag modules onto a canvas and connect them visually. Build complex multi-step automations with conditional branching, parallel execution, and data flow you can actually see. Color-coded connections trace data from input through AI processing to final output.
Connect to LLM providers and let AI nodes orchestrate tool calls autonomously. Agentic modules can loop, call tools, and make decisions within workflows — turning simple automations into intelligent processes.
Run workflows through a real-time chat interface. Type a message, select a workflow, and watch results stream back live over WebSocket. Every execution is logged with full step-by-step detail for debugging and auditing.
Build a sequence of steps once and reference it from any workflow — like a function call. Tasks have their own Input and Return nodes, version history, and dependency tracking. Disable a task and every workflow that depends on it is automatically paused.
Every capability is a module — a self-contained Python script with a manifest that defines its inputs, outputs, config, and resource needs. Drop a new module into the directory and it's automatically discovered and available in the builder palette.
Manage users, roles, credentials, and system settings from a single dashboard. Customize the entire UI — page background, sidebar, button colors, and per-module-category colors. Your instance looks like your brand.
Majordomo is built for people who want automation without giving up control.
Automate internal ops, reporting, and communication workflows without paying per-seat SaaS fees or trusting third parties with your data.
Build custom modules in Python, wire them together visually, and iterate fast. The manifest system and hot-reload mean no redeploys to test changes.
Run LLM-powered workflows with agentic tool calling, streaming responses, and token usage tracking. Keep everything on your own hardware.
Self-hosted means your credentials, conversations, and workflow data never leave your network. AES-256 encryption for stored secrets.
Everything you need to build, schedule, secure, and monitor automated workflows.
Cron-based scheduling with automatic startup. Set it and walk away.
Every save creates a new version. Roll back to any previous state instantly.
Owner, Manager, Developer, User. Granular permissions per module and feature.
Monitor LLM token usage per user, per workflow, per model. Set daily limits.
AES-256-GCM encrypted storage with per-credential salt. API keys stay safe.
Step-by-step audit trail for every workflow run. Input, output, duration, errors.
Export workflows as JSON, share with teammates, import into other instances.
Real-time status page monitoring backend, WebSocket, and module connections.
Configurable cleanup for execution logs, chat history, and activity records.
Auto-detects empty database and walks you through creating the first admin user.
Share workflows with specific users or make them public. Owner controls visibility.
Configure alerts for failures, errors, and token limits. Email, webhook, or in-app.
Clean, modern stack. No vendor lock-in. Runs on a Raspberry Pi or a rack server.