Verified project record
rowboatlabs/rowboat
A desktop AI coworker that maintains long-lived knowledge by indexing email, meetings, and Slack conversations into a backlinked knowledge graph, acting through built-in email, browser, and background agent surfaces. It runs as a local desktop application where data is stored locally in Markdown, though it requires you to bring your own models and may use remote APIs for inference and voice features.
Project overview
It addresses the problem of on-demand context reconstruction by maintaining long-lived, accumulated work knowledge locally in Markdown format.
- Project type
- AI Agent · RAG · Model Runtime
- Use cases
- Chat Assistants · Documents & Office · Meeting Notes · Knowledge Q&A
- Deployment
- Refer to project documentation
- License
- Apache-2.0
Best for
- General users, developers, and creators looking for a personal knowledge base and office automation tool that retains accumulated work context.
Key capabilities
- Indexes email, meetings, Slack and assistant conversations into a living Obsidian-style backlinked knowledge graph.
- Sorts emails into important and everything else, and automatically drafts responses using all accumulated work context.
- Agents run on events like new email or on a schedule, connecting to tools, searching the web, using the browser, or writing code.
- An isolated browser that lets the user and assistant collaborate on web tasks.
- Taps into the microphone and speaker, produces a live transcript, summarizes meetings into a markdown file, and updates the knowledge graph.
- Spins up parallel coding agents driven by the user's accumulated work context.
- Allows users to build their own work surfaces inside the application with access to tools and integrations.
- Connects to external tools and services via Model Context Protocol (MCP).
Limitations and risks
- Voice input functionality requires a Deepgram API key, establishing a dependency on an external service.
- Voice output functionality requires an ElevenLabs API key, establishing a dependency on an external service.
- Users must bring their own model, which can be configured locally via Ollama/LM Studio or hosted via an API key; the application does not include built-in models.
Getting started
- Download the latest desktop application version for Mac, Windows, or Linux, then install and open the application to begin.
Alternatives and comparisons
- Supports local AI models, APIs, local knowledge bases, and intelligent agent creation, deployable locally or via server.
- A macOS application with a built-in inference engine for local models that keeps conversations offline and data secure.
Project comparisons
Evidence and sources
- README: A desktop AI coworker with a memory of your work and built-in surfaces to act on it.
- README: Rowboat indexes email, meetings, slack and assistant conversations into a living Obsidian-style backlinked knowledge graph.
- README: Download latest for Mac/Windows/Linux: [Download](https://www.rowboatlabs.com/downloads)
- README: The built-in email client sorts emails into important and everything else. Rowboat automatically drafts responses for important email using all the work context.
- README: 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…
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control
Project Details
0