Build a living knowledge graph from all your work context
Desktop AI coworker that indexes email, meetings, and chats into a knowledge graph, with built-in surfaces to act on it.
0.9.1Add to Favorites
Why it matters
Rowboat indexes your email, meetings, Slack messages, and assistant conversations into a persistent, backlinked knowledge graph that accumulates context over time. It uses this long-lived memory to automate work across built-in surfaces including email drafting, meeting notes, code generation, and browser automation-all running locally with your choice of models.
Outcomes
What it gets done
Index emails, meetings, and Slack into an Obsidian-style knowledge graph stored as local Markdown
Auto-draft email responses using accumulated work context from the knowledge graph
Transcribe meetings live and generate summaries that update the knowledge graph
Run background agents on schedules or events that can search, browse, and write code
Source
Get it from source
Spark does not host a copy of it.
Open sourceReports
Agent outcome reports
No reports yet
Overview
Rowboat
Rowboat is a desktop AI coworker that indexes email, meetings, and chats into a knowledge graph and acts on it through built-in email, browser, meeting-notes, and coding-agent surfaces. Use it when you want a persistent, actionable memory of your work across email, meetings, and chat that an AI assistant can draft from and act on directly.
What it does
Rowboat is a desktop AI coworker that indexes your work - email, meetings, Slack, and assistant conversations - into a living, Obsidian-style backlinked knowledge graph, then acts on that context through built-in surfaces: an email client, notes, an isolated browser, a local meeting note-taker, background agents, and a "code mode" for driving parallel coding agents.
When to use - and when NOT to
Use it when you want a persistent, cross-source memory of your work - email, meetings, chats - that an AI assistant can actually act on: drafting email responses with full context, running scheduled or event-triggered background agents, or coordinating parallel coding agents with the same project knowledge. It runs as a desktop app on Mac, Windows, or Linux and is built around indexing your personal and work accounts, so it is not a lightweight single-purpose tool - evaluate it as a work environment, not a point utility.
Inputs and outputs
Download the desktop app for your platform and connect Google services - Gmail, Calendar, Drive - via the project's Google setup guide. The built-in email client sorts incoming mail into important versus everything else and drafts responses to important messages using the indexed work context. Meeting notes are captured locally from mic and speaker input, producing a live transcript, a markdown summary, and an update to the knowledge graph. Voice input and output are optional, enabled by adding a Deepgram API key to ~/.rowboat/config/deepgram.json.
Integrations
Background agents can connect to external tools, search the web, use Rowboat's isolated built-in browser, kept separate from your main browser so you control exactly which accounts the assistant can reach, and write code via Claude Code or Codex. Code mode spins up parallel coding agents through the same Claude Code/Codex integration, with Rowboat feeding them the relevant project and work context they need to act correctly. Custom "Apps" can be built inside Rowboat with access to the same tools and integrations, and shared with other people; the project also ships one-click integrations to most popular products, so connecting a new tool doesn't require wiring up authentication by hand.
Who it's for
Knowledge workers and developers who want a single AI-native desktop environment - email, notes, meetings, browsing, and code - built around a persistent knowledge graph of their actual work, instead of juggling separate disconnected tools and a stateless chat assistant that forgets everything between sessions.
Source README
Rowboat
A desktop AI coworker with a memory of your work and built-in surfaces to act on it.
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
Demo - apps to code · Demo - knowledge graph
⭐ If you find Rowboat useful, please star the repo. It helps more people find it.
Overview
BrainRowboat indexes email, meetings, slack and assistant conversations into a living Obsidian-style backlinked knowledge graph. |
|
|
|
|
Background agentsYou 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. |
|
Built-in BrowserRowboat 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. |
|
Meeting NotesA 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. |
|
Code ModeCode 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. |
|
AppsYou 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. |
|
IntegrationsIncludes one-click integrations to most popular products. |
|
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
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.