0de9589a7d
Render filepath code blocks as rich, clickable cards with three variants: knowledge files (navigate to editor), audio files (inline play/pause), and system files (open externally). Adds shell:openPath and shell:readFileBase64 IPC channels, FileCardProvider context, and Streamdown pre override. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .github/workflows | ||
| apps | ||
| assets | ||
| .env.example | ||
| .gitattributes | ||
| .gitignore | ||
| build-electron.sh | ||
| CLAUDE.md | ||
| docker-compose.yml | ||
| Dockerfile.qdrant | ||
| LICENSE | ||
| README.md | ||
| start.sh | ||
Rowboat
An open-source, local-first AI coworker with memory for everyday work
Rowboat connects your email and meeting notes, builds long-lived knowledge from them, and uses that knowledge to help get work done on your machine.
Demo
Quick start
Download for Mac:
https://github.com/rowboatlabs/rowboat/releases/latest
What it does
Rowboat ingests your:
- Email (Gmail)
- Meeting notes (Granola, Fireflies)
and organizes them into a local, Obsidian-compatible vault of plain Markdown files with backlinks.
This vault is not just for browsing or search. It becomes a working memory that Rowboat’s AI uses to take actions on your behalf.
As new emails and meetings come in, the relevant notes update automatically, building persistent context across people, projects, organizations, and topics.
How it’s 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.
What you can do with it
Rowboat uses this knowledge to help with everyday work, including:
- Drafting emails using accumulated context
- Preparing for meetings from prior decisions and discussions
- Organizing files and project artifacts as work evolves
- Running shell commands or scripts as agent actions
- Extending capabilities via external tools and MCP servers
Actions are explicit and grounded in the current state of your knowledge.
Local-first by design
- All data is stored locally as plain Markdown
- No proprietary formats or hosted lock-in
- Works with local models via Ollama or LM Studio, or hosted models if you prefer
- You can inspect, edit, back up, or delete everything at any time