Rowboat – Open-Source Claude Cowork with an Obsidian Vault
Claude Cowork just launched, bringing agentic AI to everyday work. Rowboat is an open-source alternative that builds knowledge that persists over time. A quick demo is here: https://youtu.be/T2Bmiy05FrI It connects to Gmail and meeting notes (Granola, Fireflies) and organizes them into an Obsidian-compatible vault. Plain Markdown files with backlinks, organized around things like people, projects, organizations, and topics. As new emails and meetings come in, the right notes update automatically. Rowboat is also the primary interface for this vault. You can read, navigate,…
What it does
In the maker’s words, at launch
Claude Cowork just launched, bringing agentic AI to everyday work. Rowboat is an open-source alternative that builds knowledge that persists over time. A quick demo is here: https://youtu.be/T2Bmiy05FrI It connects to Gmail and meeting notes (Granola, Fireflies) and organizes them into an Obsidian-compatible vault. Plain Markdown files with backlinks, organized around things like people, projects, organizations, and topics. As new emails and meetings come in, the right notes update automatically. Rowboat is also the primary interface for this vault. You can read, navigate, edit, and add notes directly. It includes a full markdown editor and graph visualization so you can see how context builds up across conversations. Why not just search transcripts when you need something? Search only answers the questions you think to ask. A system that accumulates context over time can track decisions, commitments, and relationships across conversations, surfacing patterns you didn’t know to look for. Once this context exists, it becomes knowledge that Rowboat can work with. Because it runs on your machine, it can work directly with local files and run shell commands or scripts, including tools like ffmpeg when needed. The link in the title opens an interactive example graph showing how context accumulates across emails and meetings. We used a founder example because it naturally includes projects, people, and long-running conversations, but the structure applies to any role. Examples of what you can do with Rowboat: draft emails from accumulated context, prep for meetings by assembling past decisions and enriching them with external research (for example via Exa MCP), organize files and project artifacts on your machine as work evolves, or turn notes into voice briefings via MCP servers like ElevenLabs. We’re opinionated about noise. We prioritize recurring contacts, active projects, and ongoing work, and ignore one-off emails and notifications. The goal is long-lived knowledge that compounds over time. All data is stored locally as plain Markdown. You can use local models via Ollama or LM Studio, or a hosted model. Apache-2.0 licensed. GitHub: https://github.com/rowboatlabs/rowboat Curious how this fits into your current workflow for everyday work.
Does the same job
all alternatives →
- VBVessel Browser – An open-source browser built for AI agents, not humansMar 2026 · quantaintellect.com · ▲6
I'm Tyler - the solo operator of Quanta Intellect based in Portland, Oregon. I recently participated in Nous Research's Hermes Agent Hackathon, which is where this project was born. I've used agents extensively in my workflows for the better part of the last year - the biggest pain point was always the browser. Every tool out there assumes a human operator with automation bolted on. I wanted to flip that - make the agent the primary driver and give the human a supervisory role. Enter: Vessel Browser - an Electron-based browser with 40+ MCP-native tools, persistent sessions that survive…
- CMCc-md – Zero-cost Obsidian sync across iPhone, Mac, and GitHubFeb 2026 · github.com · ▲8
Here's something I realized: the most AI-native knowledge base isn't a SaaS product with an API. It's a folder of markdown files on your disk. Obsidian stores everything as plain .md files. That means Claude Code (or any AI tool) can grep, read, write, and traverse your entire knowledge base with zero setup. No API keys. No OAuth. No middleware. Just local file I/O. The only missing piece was sync. I wanted my vault on iPhone (iCloud), on Mac (local), and on GitHub (backup + version history) — without paying $4/mo for Obsidian Sync. cc-md is ~400 lines of bash. iCloud handles Apple…
- NONimbalyst open source Obsidian, Codex app, and Linear for coding agentsMay 2026 · github.com · ▲7
Hi, I'm Karl. Greg and I spent the last year building Nimbalyst, an open-source local desktop workspace for working with coding agents. We want to give agents and humans one place to work together with maximum bandwidth and context, instead of Obsidian for plans, Excalidraw for diagrams, Codex app or Conductor for session management, and Linear for tasks. So we integrated: - Visual editors for markdown, diagrams, mockups, data models, CSV, code, and your own custom extensions - Red/green diff review with per-block accept/reject when an agent makes changes - Session manager with…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
