Where captured screens, audio, and transcripts live, which models run on your laptop, and what actually leaves the device.
With Overshow, OCR text, audio transcripts, and metadata sit in a local SQLCipher-encrypted SQLite database on the laptop. No screen images or video files are persisted. Cloud assistants upload the same content to their provider by default.
Overshow runs on-device speech-to-text for transcription, on-device speaker labelling, on-device semantic embeddings, and a local language model for chat. All on-device. Cloud assistants call an external API for each of those.
By default, nothing does. On Pro and Enterprise, you can enable the shipping read-only Memory MCP integration and approve individual AI clients. A query and returned snippets reach a cloud client only when you approve one; an optional source-detail grant can also return a redacted source window. Exports are manual.
Runs over short rolling windows so words are not cut off at boundaries.
Vectors indexed locally alongside full-text search.
Runs on Apple Silicon. No external LLM calls.
Install Overshow on one laptop, use it for a week on your real work, and see what you miss from a cloud assistant and what you gain from keeping data local.
This is a practical comparison, not an ideological one. Both models work. They differ in where captured data sits, which AI runs where, and what you need to explain to your security team.
Capture, transcription, search, and chat all run on the laptop.
Nothing in that list requires a network call to process your captured content.
The desktop app is local. The account does sit in the cloud, because sign-in, billing, device registration, and aggregate licence-usage counts need to. None of your captured content does. What stays on the machine is the captured content itself.
Optional paths where data does leave:
Cloud-first assistants are usually the right choice when:
Local-first is usually the right choice when:
