Work with local Mac resources
Can work with files, run terminal commands and Python, and drive native Mac apps.
Coding / product dossier
A native macOS agent that uses files, terminal, apps, MCP, and local or BYO models.
Product brief
Naseem is a native AI agent for macOS, built entirely in Swift. It can work with your files, run terminal commands and Python, drive native Mac apps, automate and test apps in the iOS Simulator, use MCP and Skills, delegate to sub-agents, and work remotely through Telegram. Bring your own model or run locally with Ollama/MLX. Every consequential action requires your approval first, and autonomous mode is strictly opt-in. No Electron. No Node. It does real work on your Mac — with you in control.
Why we selected it
A capable local-first macOS agent with unusually specific execution surfaces: files, terminal, Python, native apps, iOS Simulator, MCP, sub-agents, and local models. Approval gates and opt-in autonomy make the scope more
Product preview saved with our daily selection
Capability scan
Only capabilities supported by the product information we collected are listed here.
Can work with files, run terminal commands and Python, and drive native Mac apps.
Can automate and test apps in the iOS Simulator.
Supports MCP and Skills and can delegate work to sub-agents.
Lets users bring their own model or run locally with Ollama or MLX.
Requires approval before every consequential action; autonomous mode is strictly opt-in.
Best-fit use cases
FAQ
Naseem is a native AI agent for macOS that is built entirely in Swift.
Its description says it can work with files, run terminal commands and Python, drive native Mac apps, and automate and test apps in the iOS Simulator.
Yes. It can run locally with Ollama or MLX, and it also supports bringing your own model.
Naseem requires user approval before every consequential action. Its autonomous mode is strictly opt-in.
Yes. Its description states that it can work remotely through Telegram.