Activepieces
A self-hosted AI agent and workflow automation platform for teams, with a visual builder, MCP tools, and an MIT-licensed core.
Activepieces brings AI agents and workflow automation into one workspace for teams that need to connect their apps and internal data. It runs on your own servers with Docker or Kubernetes, or as a managed cloud service. An isolated deployment can keep platform data on its own infrastructure; connected apps and model providers may still require external access. Its core and app integration pieces are MIT-licensed.
Staff can describe a recurring job in plain language and inspect the resulting flow in a visual builder. Agents can work across connected apps and MCP servers, while human approvals can hold actions such as payments for review. A support agent, for example, can answer routine requests and pass other cases to a person. Flows support branching, retries and error handling; developers can write TypeScript for steps that need custom logic.
Agents and flows share app connections. They can read and update data in the workspace's tables, and agents can search documents in its knowledge base. Activepieces can also expose workflows through an MCP server for Claude and Cursor. For work outside its app integrations, it can call REST or GraphQL APIs. Teams can use their own AI providers, including Anthropic, OpenAI, AWS Bedrock and Google Gemini.
The separately licensed, self-hostable Enterprise Edition adds team projects, role permissions, Okta or Entra sign-in, and audit logs. It can use HashiCorp Vault for credentials and stream audit events to a SIEM such as Splunk. Workflow runs can resume from checkpoints after an interruption.
