Sandbox
@rowboatlabs/rowboat

Desktop AI coworker with memory and work surfaces

Rowboat is a local desktop app that indexes your work into a living knowledge graph and uses that context across tasks. It combines email, meeting notes, browser work, background agents, and code mode in one app, with MCP connections for external tools.

17,523 stars1.7k forksTypeScriptUpdated 6d ago
Rowboat - Cowork meets Obsidian
RowBoat (YC S24)19k views • 7 months ago

Videos about this repo

Who it's for

Builders who want an AI coworker on their desktop that can remember context and work across multiple surfaces.

What it delivers

You can keep work context in one place and let the app act on it instead of re-explaining everything.

What it does

Living knowledge graph

Indexes email, meetings, Slack, and assistant conversations into a backlink-style graph stored locally as Markdown.

Built-in email client

Sorts mail into important and everything else, then drafts replies using your work context.

Background agents

Runs agents on events or schedules, with access to tools, web search, browser actions, and code via Claude Code or Codex.

Built-in browser

Provides an isolated browser surface so the assistant can do web tasks in accounts you choose.

Meeting notes

Records mic and speaker audio, makes live transcripts, writes markdown summaries, and updates the knowledge graph.

Code mode

Spins up parallel coding agents with Claude Code or Codex and gives them the current work context.

MCP integrations

Connects to external tools and services through Model Context Protocol, including search, databases, CRMs, Slack, Linear, Jira, and GitHub.

Custom apps

Lets you build your own work surfaces inside Rowboat and share them with other people.

How to get it

  1. 1All API key files use the same format
    {
      "apiKey": "<key>"
    }

README

rowboat-github-2

Rowboat

A desktop AI coworker with a memory of your work and built-in surfaces to act on it.

rowboatlabs/rowboat | Trendshift

Website Discord Twitter Y Combinator

简体中文 · 日本語 · 한국어 · Español · Français · Português

Rowboat indexes your work into a living knowledge graph and uses that to get work done on your machine. It includes work surfaces for collaborating with AI: email client, notes, browser, code mode, meeting note taker, and workspaces for different projects.

Download latest for Mac/Windows/Linux: Download

Rowboat Apps to Code demo

Demo - apps to code · Demo - knowledge graph

⭐ If you find Rowboat useful, please star the repo. It helps more people find it.


Overview

Brain

Rowboat indexes email, meetings, slack and assistant conversations into a living Obsidian-style backlinked knowledge graph.
Brain graph screenshot

Email

The built-in email client sorts emails into important and everything else. Rowboat automatically drafts responses for important email using all the work context.
Email screenshot

Background agents

You can set up background agents that run on events like new email or on schedule like every day at 8am. They can connect to tools, search the web, use the browser and write code using Claude Code or Codex.
Background agents screenshot

Built-in Browser

Rowboat includes a browser that lets you and assistant collaborate on web tasks. Because it's isolated from your main browser, you can log in only to the accounts that want the assistant to access.
Browser screenshot

Meeting Notes

A local meeting note-taker that taps into mic & speaker, produces live transcript and summarizes the meeting in a markdown file and updates the knowledge graph.
Meeting notes screenshot

Code Mode

Code mode lets you spin up parallel coding agents with Claude Code or Codex, and have Rowboat drive them with all the work context where needed.
Code mode screenshot

Apps

You can build your own work surfaces inside Rowboat — they get access to all the tools and integrations, and you can share them with other people.
Apps screenshot

Integrations

Includes one-click integrations to most popular products.
Integrations screenshot

Installation

Download latest for Mac/Windows/Linux: Download

All release files: https://github.com/rowboatlabs/rowboat/releases/latest

Google setup

To connect Google services (Gmail, Calendar, and Drive), follow Google setup.

Voice input

To enable voice input and voice notes (optional), add a Deepgram API key in ~/.rowboat/config/deepgram.json

Voice output

To enable voice output (optional), add an ElevenLabs API key in ~/.rowboat/config/elevenlabs.json

Web search

To use Exa research search (optional), add the Exa API key in ~/.rowboat/config/exa-search.json

External tools

To enable external tools (optional), you can add any MCP server or use Composio tools by adding an API key in ~/.rowboat/config/composio.json

All API key files use the same format:

{
  "apiKey": "<key>"
}

How it’s different

Most AI tools reconstruct context on demand by searching transcripts or documents.

Rowboat maintains long-lived knowledge instead:

  • context accumulates over time
  • relationships are explicit and inspectable
  • notes are editable by you, not hidden inside a model
  • everything lives on your machine as plain Markdown

The result is memory that compounds, rather than retrieval that starts cold every time.

Bring your own model

Rowboat works with the model setup you prefer:

  • Local models via Ollama or LM Studio
  • Hosted models (bring your own API key/provider)
  • Swap models anytime — your data stays in your local Markdown vault

Extend Rowboat with tools (MCP)

Rowboat can connect to external tools and services via Model Context Protocol (MCP). That means you can plug in (for example) search, databases, CRMs, support tools, and automations - or your own internal tools.

Examples: Exa (web search), Twitter/X, ElevenLabs (voice), Slack, Linear/Jira, GitHub, and more.

Example: Parallel web search

Parallel Search MCP provides web_search and web_fetch for public web search and page extraction without a Parallel account or API key. Free access is rate limited.

Open Settings → MCP Servers, add the parallel entry to your existing mcpServers object, and click Save. Keep any other server entries. If no servers are configured, use:

{
  "mcpServers": {
    "parallel": {
      "url": "https://search.parallel.ai/mcp"
    }
  }
}

This connects through Rowboat's existing Streamable HTTP client. Ask Rowboat to list the tools on the parallel server, then try: "Use Parallel to find the official MCP documentation."

Once configured, Rowboat can invoke these tools during its work, subject to your MCP tool permissions. Queries, requested URLs, and any supplied objectives or context are sent to Parallel. This setup leaves Exa and other configured providers unchanged. To remove it, delete the parallel entry in Settings → MCP Servers and save.

Local-first by design

  • All data is stored locally as plain Markdown
  • No proprietary formats or hosted lock-in
  • You can inspect, edit, back up, or delete everything at any time

Files in the repo

Repository payload9 top-level entries
  • .github
  • apps
  • assets
  • docs
  • .gitignore
  • google-setup.md
  • LICENSE
  • proposal.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More other

🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.

95k
HKUDS/
Vibe-Trading

"Vibe-Trading: Your Personal Trading Agent"

33k
tinyhumansai/
openhuman

OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research.

40k

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

35k

AIPOCH Open-Science is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.

4k