activepieces and golf
About activepieces
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
Pieces are TypeScript npm packages with hot-reload support for local development, automatically published to npmjs and exposed as MCP servers for LLM integration in Claude Desktop, Cursor, and Windsurf. The platform combines a visual no-code builder with programmatic extensibility, supporting flow control (loops, branches, retries), human-in-the-loop approval workflows, and native AI pieces for agent building. Self-hosted architecture provides network isolation and full data control while maintaining enterprise customization options.
About golf
golf-mcp/golf
Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
Implements automatic component discovery via file-system conventions (tools, resources, prompts as Python modules) with Pydantic schema inference, eliminating manual server registration. Supports multiple transports (SSE, streamable-HTTP, stdio) and integrates OpenTelemetry for distributed tracing. Built-in auth layer handles JWT, OAuth Server, API keys, and dev tokens—all configured declaratively in `auth.py`.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work