I know this sounds like a privacy pitch. It is. But it's also just something true that most people have never bothered to think about. Every AI tool you've been using has been sending your documents to a server. The model reads them. A system logs them. Some of it trains future models. Keel runs entirely on your GPU, inside your browser tab. Nothing leaves. Not the question. Not the answer. Not the filename.
"I had a 200-page due diligence report I couldn't send to anyone. Asked Keel to find every earn-out clause and flag the risk language. Six seconds. Cited every page number. The file never left my laptop."
M&A associate · beta tester
I'm not trying to scare you. Well, maybe a little. But this isn't paranoia. It's literally just what the terms say. Most people just never scroll past the headline.
The biotech founder at 11pm asking an AI to structure the patent filing she's three years from submitting. The M&A lawyer typing deal questions he can't ask his colleagues. The therapist drafting session notes with a patient's name in the document. Every one of those queries hit a server. The model read it. A system logged it. Some of it will train future models.
"But the companies say they don't—" They do. Open the terms. Scroll past paragraph eight.
The AI was never the product. Your information was. That's the business model. That's how the GPUs get paid for. It's not malicious. It's just the deal you agreed to without reading it.
Keel is a different deal. You pay $49.99 a month. Your GPU runs the model. Your disk holds the documents. Your browser contains the conversation. When you close the tab, it's gone the way a thought disappears when you stop thinking it.
Not archived. Not retained. Not flagged for review by someone you've never met.
"I'm a criminal defense attorney. What my clients tell me cannot be on anyone else's server. Full stop. Keel is the first AI where that's structurally true. Not just a policy I have to hope they're following."
Criminal defense attorney · beta tester
most RAG tools do one pass and hope. keel breaks your question into sub-queries, runs them in parallel, then scores every candidate through a cross-encoder before writing a word. the lawyer who asks "what are the indemnification obligations?" gets clause 14.3(b). not a paragraph that gestures near it. every sentence traces to a source.
your login token leaves your browser. your billing status leaves your browser. that's the complete list. the document, the query, the answer. none of it was ever on a wire. you don't have to trust our privacy policy. there's nothing for it to cover.
keel reads your GPU at startup, loads the largest model that fits your VRAM, and begins. 7B on a base M3 or RTX 4060. up to 70B on an M3 Max or RTX 4090. not throttled by someone else's queue. your GPU, full speed, answers the moment you hit enter. it tells you exactly which model you're running.
the founder who uploads three years of board decks and asks "when did we first discuss a Series B?" gets a precise answer. not because it's in the cloud. because a real vector database with BM25 and semantic hybrid search ran the query locally. restart your browser. it's still there. always was.
PDF, Word, Excel, Markdown, plain text, code. four browser workers parse in parallel. chunks overlap at boundaries so nothing gets cut. a 50-page document is ready in under 4 seconds. after that it lives on your disk until you delete it. nobody else ever sees it.
keel reads your GPU at startup and loads the largest model that fits your VRAM. on a base M3 or RTX 4060: 7B, quantized. on an M3 Max or RTX 4090: up to 70B. as the hardware gets bigger, the model gets bigger with it. different hardware. same guarantee: nothing leaves the machine.
if you've never thought about what happens to your documents when you use AI, this probably isn't for you. if you have. welcome. flat monthly price. no per-query billing. your GPU does the compute.
try it. no card required. if you hate it, you've lost nothing except maybe the assumption that private AI couldn't exist.
for anyone whose documents contain something they'd be embarrassed to see logged on a stranger's server. you know who you are.
for teams where the legal or compliance person has opinions about what happens to company data. they're right, by the way.
there was. it just took a while to build. we're opening to a small first group. lawyers, founders, researchers, and engineers whose work is too sensitive to hand to a server. if that's you, you already know it. get two months of pro free when we launch.
one email when we're ready. nothing before that.