Hexabot

Hexabot is an AI workflow automation platform for teams building customer service assistants and business automations. It links customer conversations to actions while letting teams keep workflow data on their own infrastructure.

• Workflow design: Build flows in a visual graph editor or portable YAML, with triggers for chat, forms, schedules and events.
• Actions and tools: Connect model calls, APIs and back-office systems through reusable actions with validated inputs and outputs.
• Memory and knowledge: Give agents persistent context through managed memory and retrieval-augmented generation, and connect external tools through MCP.
• Human handoff: Use conditions, loops and inbox workflows to route cases to support staff when an assistant needs human judgment.
• Service channels: Run multilingual assistants across websites, messaging platforms, social channels and custom entry points.

You can run Hexabot locally, on-premise or in your own cloud. Workflows, memory and customer data remain in infrastructure you control; workflows can also call external models and services. Developers can extend the runtime with custom actions, channels and helpers. SQLite is the default local database, and Postgres supports production deployments. Docker is optional for Docker-based services.

Hexabot is source-available under the Fair Core License 1.0 with an ALv2 Future License. It has free and paid self-hosted offerings, and the full codebase is available to inspect and extend.