Open-source AI coworker, with memory https://www.rowboatlabs.com
Find a file
Ramnique Singh 125d39ee0b feat(x): per-turn reasoning effort — core plumbing
Adds a canonical reasoning-effort ladder (low|medium|high, absent =
auto/provider default) that travels: send config → turn_created.config →
every model call's persisted parameters (§8.3) → provider-specific
options at invoke time. Behavior-neutral: nothing sends an effort yet,
and auto produces byte-identical requests to today.

- shared: ReasoningEffort enum (single source, reused by models.json
  provider config), TurnCreated.config.reasoningEffort (additive
  optional on a non-strict object — old builds strip it, no
  schemaVersion bump), sessions:sendMessage IPC schema.
- turns: CreateTurnInput/SendMessageConfig/HeadlessAgentOptions carry
  the value; runModelStep stamps it on each call's parameters so every
  step durably records what it ran with.
- bridge: maps canonical effort to provider options, transport-only
  like prompt caching — OpenAI reasoningEffort, Anthropic thinking
  budgets (raising maxOutputTokens to the budget floor, never lowering
  an explicit value), Gemini thinkingLevel/thinkingBudget by
  generation, OpenRouter/rowboat reasoning.effort. Capability-gated
  via a cache-only models.dev lookup (never blocks a turn on the
  network); unknown support fails closed on strict flavors, while
  OpenRouter-shaped flavors map permissively since OpenRouter drops
  the field for non-reasoning models. Explicit persisted
  providerOptions win over the mapping. Ollama keeps its existing
  provider-level think rewrite; openai-compatible endpoints get
  nothing (no safe universal parameter).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 10:11:25 +05:30
.github/workflows remove irrelevant gh workflows 2026-07-09 16:35:41 +05:30
apps feat(x): per-turn reasoning effort — core plumbing 2026-07-10 10:11:25 +05:30
assets Readme updates (#58) 2025-04-03 23:35:15 +05:30
.env.example Run mongodb in docker 2025-04-07 13:30:27 +05:30
.gitattributes Mega UI revamp 2025-04-03 17:56:31 +05:30
.gitignore chore: remove meeting-prep PLAN.md from repo (keep local-only) (#652) 2026-07-02 00:44:28 +05:30
build-electron.sh wip-electron 2026-01-16 12:05:33 +05:30
CLAUDE.md popout and full screen work as expected 2026-07-04 12:06:32 +05:30
docker-compose.yml merge job workers 2025-08-17 11:06:53 +05:30
Dockerfile.qdrant improve embedding index docs and setup 2025-05-09 09:38:09 +05:30
google-setup.md feat(oauth): switch Google OAuth from PKCE to authorization code flow with client secret 2026-04-10 00:43:34 +05:30
LICENSE Fill license placeholder 2025-01-31 16:29:39 +05:30
README.md Include demo video link in README 2026-07-07 18:43:05 +05:30
start.sh Revert auth related changes to start.sh 2025-09-16 16:55:29 +04:00

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

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 demo video

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.
Screenshot 2026-06-24 at 11 22 52 PM

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 its 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 bulild your own work surfaces inside Rowboat — they get acess 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

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 its 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.

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