TinkerPilot

Your truly local AI assitant, to be used for coding assistance, summarization, meeting transcription, task management, and developer utilities. It is lightweight and can be run on almost any local machine. For example, macbook air m1 with 8gb ram can run it smoothly.

All operations and features are powered by on-device AI inference. No cloud APIs. No data leaves your machine.

Privacy & Security

• All AI inference runs locally on your hardware (via Ollama)
• No data is sent to any cloud service
• All data stored in ~/.tinkerpilot/ on your local filesystem
• Apple Notes access requires explicit macOS permission grants
• No telemetry, no analytics, no tracking

For a detailed look at the architecture, see the Architecture Overview.