Theme
AI Resources
Rowboat
Rowboat is an open-source desktop AI coworker that turns email, meetings, notes, and assistant conversations into an editable knowledge graph, then uses that context across the work people do next.
Its built-in surfaces include email, meeting notes, an isolated browser, code mode, project workspaces, small apps, and background agents. The knowledge graph is stored as linked Markdown files on the user's machine, while model providers and connected services remain separate choices. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
A desktop coworker built around work memory
Rowboat links people, projects, decisions, meetings, messages, and assistant conversations in a Markdown knowledge graph that can be read and edited outside the chat window.
Why it stands out
The memory follows the next piece of work
The same context can help prepare for a meeting, draft an email, support a browser task, guide a coding agent, or feed a small project app instead of starting cold in each surface.
Availability
Desktop downloads and public source
The project provides desktop downloads for macOS, Windows, and Linux, a public GitHub repository, and an Apache-2.0 license declared by the repository.
Why it matters
What makes it useful
Work context is often scattered across inboxes, meeting notes, project files, and old chats. Rowboat keeps a linked record in ordinary Markdown and brings the relevant parts into the next task, so a meeting decision can inform an email, a document, or a coding session without being explained again from scratch.
What to know
Where it fits
Rowboat fits the desktop productivity layer: it combines a personal knowledge graph with surfaces where work is read, discussed, written, automated, and reviewed. It is most useful when the same projects and relationships recur across several tools, rather than for a single short chat or one isolated document search.
Notable points
What stands out
The project keeps its knowledge graph in an Obsidian-style, plain-Markdown vault and lets users choose local or hosted models. Email, calendar, meeting, search, voice, MCP, and other integrations can add their own accounts, permissions, API keys, and outside data paths.
Before using
What to review
Choose what belongs in long-term work memory before connecting an inbox, calendar, meeting stream, Slack, or assistant history.
Treat local Markdown storage and outside processing as separate questions: hosted models, web search, voice services, MCP servers, and connected apps may send task data beyond the machine.
Review each background agent's trigger, tools, files, browser accounts, approval points, and stop path before letting it run on events or a schedule.
Check the current platform download, permissions, account setup, provider costs, and integration requirements before relying on it for daily work.
Back up or export the Markdown vault and test how important work can be recovered without the app.
Reader fit
Who may find it relevant
People whose meetings, email, notes, projects, and assistant chats keep referring to the same decisions and relationships.
Readers who want AI memory to remain visible and editable as ordinary files instead of living only inside a chat service.
Builders who want background agents, browser tasks, coding agents, and small apps to share project context.
Less relevant for someone who wants a fully offline result without checking model and integration data paths, or only needs a simple one-purpose assistant.
Editorial note
Why LifeHubber lists it
Rowboat connects durable, editable work memory to the places where that memory can save real effort: the next meeting, reply, document, browser task, code change, or scheduled follow-up. That makes it a useful reference for deciding how much context an AI coworker should keep and how much access it should have.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
What to explore next
Decide what the coworker should remember and reach.
Rowboat can carry work context across email, meetings, browsing, coding, and scheduled agents. These guides help separate useful memory from unnecessary retention and set limits before an agent acts through connected tools.
More in AI Agents
Keep browsing this category
Explore more AI agent projects.
Agent-Reach
Panniantong/Agent-Reach
A CLI routing layer that helps command-capable agents reach web, social, repository, video, RSS, and search sources through ordered backends. For multi-backend channels, its doctor command reports the active backend, while default setup only checks the machine unless system changes are explicitly authorized.
AIPOCH Medical Research Skills
aipoch/medical-research-skills
A curated library of medical research agent skills designed to support evidence review, protocol design, data analysis, and academic writing workflows.
Claude Code Game Studios
Donchitos/Claude-Code-Game-Studios
A multi-agent game-development studio system for Claude Code, organized around specialized agents, workflow skills, hooks, rules, and templates.
