What “it stays on the machine” means exactly.

A program on the laptop. No server, no account, no admin view.

• Recordings as 16 kHz WAV and transcripts as Markdown in Documents/Meetings or a folder of your choice.
• Speech models and search index under %LOCALAPPDATA% or ~/Library/Application Support, never in the roaming profile.
• Log files with device changes, errors and timings. No speech.

The model download on first launch (596 MB, pinned addresses at github.com, every file verified by SHA-256). The update check, when someone presses the button in Settings (pinned manifest, package verified against a key built into the program). A feedback report, when someone writes one and presses Send; Settings shows every byte first. Onsite starts the model download, automatically whenever a model is missing at launch (on first start, after an update that adds one, or to finish a failed download); everything else only when you click a button. No timer, no telemetry, no crash reporting.

All three use the system proxy and the operating system certificate store. To verify: start Onsite, wait for the download, record a meeting and watch the process with Wireshark, Resource Monitor or nettop. No connection should appear.

• Microphone: your side of the call.
• System audio: the other side. “Screen and System Audio Recording” on macOS; loopback needs no permission on Windows.
• Accessibility (macOS): only to paste dictations and to recognise browser meetings by window title.

No screen recording, no calendar, no contacts.

• Windows: per-user installer, no admin rights, silent with Onsite-x64-setup.exe /S.
• macOS: drag to Applications. Permissions survive updates.
• The model folder of one set-up machine can be copied to the others.
• Settings are one JSON file in the user profile: folder, retention, automatic recording.
• Audio: keep everything, delete after 30 days, or delete once transcribed. Transcripts stay.

Under Settings › Agents the user can switch on two doors that otherwise do not exist. An MCP server reads the transcripts for an AI assistant on the same machine: read-only, over stdin and stdout, started by the assistant as Onsite --mcp. A command line controls the running program through a local socket, a Unix domain socket file on macOS and a named pipe on Windows. Neither opens a network port, and both refuse to serve while the switch is off.

What an assistant does with the transcripts once it has them is up to the assistant. A cloud assistant sends them to its provider. That is why the switch stays off until the user turns it on deliberately.

After the alpha, a one-time licence per machine, verified offline by Ed25519 signature, no expiry. Activation sends the purchase code and a salted machine hash, nothing else.

POST /v1/activate
{ "code": "ONSITE-XXXXX-XXXXX-XXXXX-XXXXX", "machine": "<64 hex, salted hash>" }

Machines without internet get a signed key to paste in. A team code allows a fixed number of activations.

Every version is on GitHub with its SHA-256 checksum. The speech models are CC-BY-4.0 or MIT; a test in the build refuses any other licence. The installers will be signed before sales open.