TL;DR

Rowboat is an open-source AI coworker with two parts. (1) Memory: it turns your email, meetings, and notes into a living knowledge graph, saved as plain Markdown files on your disk. (2) Work surfaces: a built-in email client, meeting notetaker, notes, and browser, plus apps you can build or install from the community. The assistant helps inside the work itself, not just in chat.

16,600+ GitHub stars - Front page of Hacker News twice in 2026.

https://github.com/rowboatlabs/rowboat · https://www.rowboatlabs.com

https://www.youtube.com/watch?v=et5yQABJ3xI

Hey, we're Arjun and Ramnique.

At our previous startup, we built a deep-learning product for enterprise support reps at Fortune 100 brands like P&G. The models took live notes, suggested replies, and recommended actions while reps were on calls or handling emails. Coinbase acquired us in 2021. One lesson stuck: it's not enough for the AI to be right. The help has to show up where the work is happening.

So we built Rowboat around what we call "work surfaces": dedicated areas for email, meetings, notes, browser, and parallel coding, where the assistant helps inside the workflow itself rather than only through chat.

• Email client: Rowboat has a simple email client that sorts incoming emails into important vs. everything else, and pre-creates drafts for important emails. As you edit and send emails, it takes notes on your style, so future drafts get closer to your voice.
• Meeting notes: We built a Granola-style local meeting notetaker. Notes are stored as plain Markdown files on your machine. After a meeting, Rowboat feeds the notes back into the knowledge graph and updates the relevant people, project, and topic notes.
• Browser: We added a built-in browser, isolated from your main one, where you can log in only to the accounts you want the assistant to help with. The assistant uses browser-use skills to navigate websites.
• Parallel coding: The code-mode inside Rowboat lets you spin up multiple instances of Claude Code or Codex and either work with them directly or let Rowboat use your work context to orchestrate them. We built an ACP (Agent Client Protocol) client in Rowboat for this.
• Notes: Rowboat has an Obsidian-style local note-taking system. It comes with graph view, bases view, and voice notes. You can also sync Google Docs files and edit them inside Rowboat.

An example email work surface - triage plus pre-drafted replies in your voice:

You can also build your own work surfaces inside Rowboat (web apps). Each app gets its own UI and a background agent, and can use all of Rowboat's tools, product integrations, and your work memory. For instance: an app to manage GitHub activity, project tracking, or ads campaign management. There are a few community apps at launch that you can search and install. Publishing your own is one click from inside Rowboat: connect your GitHub and it creates the repo and registers the app for you.

All of this is powered by the Brain: a knowledge graph of your work that Rowboat builds and maintains automatically, so every surface starts with full context. We did a Show HN on it a few months back: https://news.ycombinator.com/item?id=46962641.

As an example that ties some of these together: you can create an app inside Rowboat that collects feature requests from your email, meetings, and Slack and ranks them, then uses Claude Code to draft a first version of the top-ranked feature, pulling prior context about it from your knowledge graph.

Rowboat is local-first: data is stored as plain Markdown files you can read, edit, or delete anytime. It is Apache-2.0 and works with any LLM, including local models through Ollama or LM Studio. You can also use your ChatGPT subscription. It works on Mac, Windows and Linux.

Shipped in public

Every major Rowboat release has launched on Hacker News:

• Rowboat CLI (Nov 2025): front page, 131 points. A Claude Code-style CLI agent for everyday work, two months before Anthropic's Cowork.
• Rowboat Knowledge (Feb 2026): front page, 205 points, #1 on GitHub Trending. A living knowledge graph as plain Markdown, two months before Karpathy's viral LLM-wiki post.
• Rowboat Work Surfaces (Jul 2026): front page, 219 points.

How you can help

• Try it: https://www.rowboatlabs.com (Mac, Windows, and Linux)
• Star the repo: https://github.com/rowboatlabs/rowboat
• Send it to one friend who lives in email and meetings