Seeker is a local-first personal AI agent platform: a shell that holds AI, filled with mini-apps you can switch on and off. Open source (MIT), on macOS, Windows, and the web.

What it is.

Conversation is the entry: say what you need, and the agent decides whether to query your data, produce a card, or run a skill you've saved; the right-side canvas appears only when something needs showing. The first built-in app is a job-hunting workbench — matching roles, polishing resumes, interview practice, market-value estimates; switch it off entirely when you're done, and the data stays. What it wants to be is not another chat box, but a personal workbench that grows on your own data.

Why it exists.

Most AI tools keep your data on someone else's server. Seeker inverts that: data lives on your machine by default (SQLite on desktop), and the network is used only to call the model endpoints you configured yourself; API keys go only into the system keychain — never files, never logs; private fields like names and phone numbers sit in a separate store the AI structurally cannot read — not a promise not to read, but the absence of a path. Even which business data the AI may query passes three gates: the app is on, the app declared it, and you granted it by hand. All three, or nothing.

Restraint, by design.

No red-alert UI, no countdown pressure; every deletion is undoable, and bulk or clear-all actions require a preview and confirmation. The AI can only propose destructive operations — execution always waits for your hand, and that confirmation cannot be forged by the model at the code level. The AI also cannot schedule tasks for itself, cannot edit project instructions, cannot change settings through chat: the paths to self-perpetuation deliberately do not exist.

Under the hood.

Tauri 2 (Rust core + system WebView), a native HTML/CSS/JS front end with zero frameworks — the installer is about 7MB and it opens instantly. The platform layer and the app layer are physically separated and speak only through contracts; adding an app is roughly a directory plus a manifest.

The story behind it.

This project was built by one person pairing with AI: the AI wrote the code, I steered — through a hundred-plus rounds of independent review. Every security red line is pinned by a test; every "undoable" was verified to be real. It is a product, and also an experiment in how seriously a human + AI pair can do engineering.

Try it now.

  • —Online (no install; data stays in your browser): seeker.aklman.com
  • —Desktop download (macOS / Windows): github.com/aklmans/seeker/releases
  • —Source & docs (MIT): github.com/aklmans/seeker

Current version v0.1, collecting its first real feedback — smooth or rough, I want to hear it.