Show HN: Rowboat – AI coworker that turns your work into a knowledge graph (OSS)

Source: Hacker News

Overview

AI agents that can run tools on your machine are powerful for knowledge work, but they’re only as useful as the context they have. Rowboat is an open‑source, local‑first app that turns your work into a living knowledge graph (stored as plain Markdown with backlinks) and uses it to accomplish tasks on your computer.

Example: “Build me a deck about our next quarter roadmap.”
Rowboat pulls priorities and commitments from your graph, loads a presentation skill, and exports a PDF.

• Repository:
• Demo video:

Rowboat Architecture

1. Living Context Graph

• Connects to sources such as Gmail, meeting notes (e.g., Granola, Fireflies), and voice memos.
• Extracts decisions, commitments, deadlines, and relationships.
• Writes them locally as linked, editable Markdown files (Obsidian‑style), organized around people, projects, and topics.
• Updates automatically as new conversations occur; changes (e.g., a deadline shift) propagate back to the original commitment.

2. Local Assistant

• An agent with local shell access and MCP (Multimodal Conversational Programming) support.
• Uses the context graph to perform real work on your machine, either on demand or as scheduled background tasks.
• Example: “Prep me for my meeting with John and create a short voice brief.”
  • Pulls relevant context from the graph.
  • Generates an audio note via an MCP tool like ElevenLabs.

Why Not Just Search Transcripts?

• Passing gigabytes of email, docs, and calls directly to an AI agent is slow and lossy.
• Search only answers the questions you think to ask.
• A system that accumulates context over time can:
  • Track decisions, commitments, and relationships across conversations.
  • Surface patterns you didn’t know to look for.

Licensing & Compatibility

• Apache‑2.0 licensed.
• Works with any LLM, including local models.
• All data is stored locally as Markdown, which you can read, edit, or delete at any time.

Background

The author’s previous startup was acquired by Coinbase, where work involved graph neural networks. Rowboat revisits graph‑based systems, aiming to provide the “work memory” layer that agents currently lack.

Call for Feedback & Contributions

We’d love to hear your thoughts and welcome contributions!