# Gocrewwai

A strictly-typed, Go-native alternative to CrewAI for orchestrating parallel AI agents, with LangGraph-style durable flow persistence, agent-to-agent and MCP protocol support, human-in-the-loop approvals, and security-hardened tool execution.

Gocrewwai is a high-performance agentic orchestration framework for Go, inspired by CrewAI, LangChain and LangGraph, aimed at production use: goroutine-based concurrency gives true parallel agent execution, every LLM response is unmarshaled into strictly typed Go structs rather than handled as loosely typed data, and the whole orchestrator compiles into a single zero-dependency binary.

Durable flows checkpoint state to SQLite or Redis after every node so long-running workflows can pause, resume and time-travel; human-in-the-loop interrupts and approvals work from the CLI or a real-time dashboard; agents can reflect on and correct their own work through internal loops or peer-review crews; native OpenTelemetry tracing gives vendor-neutral observability; and it supports the Model Context Protocol with local and remote servers, and agent-to-agent protocols for decentralized agent swarms with peer health checks.

Code execution runs in hardened Docker sandboxes with no network, dropped capabilities, a read-only filesystem and a process limit; URL-fetching tools validate schemes and block private IP ranges against SSRF; shell commands are matched against an explicit whitelist that denies everything by default; dangerous tools such as file writes, HTTP requests, database operations and code execution require explicit human approval; and API authentication uses constant-time comparison with a request body size limit. Built with Go; MIT licensed; alpha and beta status heading toward a 1.0 release.

Website: https://github.com/Ecook14/gocrewwai