CrewAI (open source) on a Mac

Multi-agent crews; Python framework + CLI (local) · AI / LLMs

The open-source CrewAI framework: define a *crew* of role-playing agents with goals, tools and tasks, then run it locally. It's a Python library plus a CLI, not a server; install with uv tool install crewai (or pip install crewai), scaffold with crewai create crew, and execute with crewai run; projects are config-first (agents/tasks files) with Python for the glue. Because there's no daemon or port, FrontierStack manages it as a local toolchain: it detects the crewai CLI and its version, and running crews show up in the Agent Platforms board's local-instance sweep. Distinct from the CrewAI Enterprise/AMP entry, which is the hosted control plane with its own API and deployments; use this one when the crews run on your own machine or server.

Run CrewAI (open source) with FrontierStack

Install or connect CrewAI (open source); then check its status, ports and certificate from FrontierStack. The same screen links to firewall checks, Malware Audit and backups where they apply.

Related in AI / LLMs

• Vane (Perplexica)
• MLX
• Needle 2
• TurboFieldfare
• Cerebras
• Darkbloom
• MLX (Apple)
• vLLM