Coming soon

Your entire
working life,
understood.

A knowledge graph of everything you do. Browser history, meetings, files, code -- connected and queryable. Running entirely on your machine.

On-device. No cloud. No training on your data.

your digital twin

Sources

Browser
Meetings
Files
Code
Email

Recent

pricing strategy
Q3 roadmap call
auth refactor
competitor.pdf
Q3 call mentioned auth refactor as the blocker
auth module modified 3 days after that meeting
you read 4 articles on JWT vs session tokens that week
competitor analysis flags auth as their weak point

AI tools forget everything
the moment the chat ends.

You paste the same context into every session. Your knowledge is scattered across 12 apps and none of them talk to each other.

Cannot find what you have seen

That article from last Tuesday. That Slack thread from two weeks ago. Gone from every tool you use.

Constant re-explaining

Every AI session starts blank. You paste the same background into every conversation, every time.

Connections stay invisible

The meeting, the doc, and the code are all related. No tool shows you how they connect.

Three steps to your digital twin

01

Captures everything

Browser history from Chrome and Safari. Meeting transcripts. Files, emails, code, PDFs, images. Every artifact of your working day, continuously.

02

Builds the graph

Every piece of information becomes a node. Relationships -- calls, citations, concepts -- become edges. A live map of your knowledge that grows with you.

03

You query it

Ask anything. "What connects this meeting to that codebase?" "What did I read about pricing last month?" Answers in seconds, with sources.

Everything you touch,
connected.

Not just meetings. Not just code. Your entire working context -- captured, structured, and queryable.

Browser history

Chrome, Safari, Firefox. Every page becomes a node. Search patterns reveal what you were thinking and when.

Meetings

Automatic transcription and extraction. Decisions, action items, concepts -- all connected to your wider context.

Code

AST-level extraction across 20 languages. Functions, classes, call graphs -- your codebase becomes part of the twin.

Docs and files

PDFs, Word docs, Markdown, spreadsheets. Papers you have read, specs you have written -- all in the graph.

Images and diagrams

Whiteboards, screenshots, architecture diagrams. Vision extraction connects images regardless of language.

Surprising connections

The graph surfaces relationships you did not know existed -- across browser sessions, meetings, and files from months apart.

Built for everyone
who works with knowledge

If your work involves reading, writing, deciding, or advising -- your context belongs to you.

Business Leadership

Founders, executives, board members, managers

Your decisions span hundreds of conversations, reports, and board calls. By the time a strategy is revisited, the context that shaped it has scattered across emails, Notion pages, and faded memories. Penpax connects all of it into a living graph so you always know what led to what -- and why.

Understand which meeting influenced a pricing change months later

Walk into board reviews with full context, not a search session

Connect team commitments across scattered documents and calls

Example query

"What discussions led to the Series B pricing decision?"

Investor call (Feb 12) flagged $18/seat as ceiling for SMB
Sales deck revised to $15 four days later
Competitor benchmarks tab was open 11 times that week
CFO email: "hold at 15 until pipeline clears"

Recall vs relationships

Other tools help you find things. We help you understand how they connect.

Others Penpax
Find past information Yes Yes
Meeting transcription Yes Yes
Browser history awareness No Yes
Code and AST understanding No Yes
Relationship graph, not just search No Yes
Runs entirely on-device No Yes
No cloud, no training on your data No Yes

Your twin lives on
your machine.

We do not see your data. We cannot. It never leaves your device.

On-device only

Runs entirely on your hardware. Nothing leaves.

No cloud

No servers, no sync, no third-party exposure.

Never trained on

Your data is yours. We never touch it.

What stays on your machine

  • All your captured data
  • Your knowledge graph
  • Browser history and meeting transcripts
  • Query results and insights
  • Everything. Always.

What we never do

  • Store your data on our servers
  • Train models on your content
  • Sell or share your information
  • Require internet to function
  • Phone home. Ever.

Be first to try it.

Join the waitlist and we will reach out when Penpax is ready.

No spam. Unsubscribe anytime.