activepieces/activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
What it solves
Activepieces provides an open-source, self-hosted alternative to Zapier, allowing users to automate workflows between different software services without needing to write complex code. It bridges the gap between technical developers who can build custom integrations and non-technical users who can deploy them via a no-code builder.
How it works
The platform uses a "pieces" framework written in TypeScript. These pieces are essentially npm packages that act as connectors to various services (like Google Sheets, OpenAI, and Discord). Users can assemble these pieces into "flows" using a visual builder that supports logic like loops, branches, and auto-retries. Additionally, these pieces are compatible with the Model Context Protocol (MCP), meaning they can be used as tools by LLMs in environments like Claude Desktop, Cursor, or Windsurf.
Who it’s for
- Non-technical users who want to automate business processes using a no-code interface.
- Developers who want to build and publish type-safe integrations using TypeScript.
- Enterprises requiring secure, self-hosted, and network-gapped automation tools to maintain control over their data.
Highlights
- MCP Integration: Over 280 pieces are available as MCP servers for use with LLMs.
- AI-First Capabilities: Includes native AI pieces and an AI SDK for creating custom agents within flows.
- Extensible Ecosystem: A large library of 200+ open-source pieces, many contributed by the community.
- Human-in-the-Loop: Supports execution delays and manual approval steps.
- Flexible Interfaces: Built-in support for chat and form interfaces as triggers.