Rowboat
Productivity
ai work assistant
SHOW HN2026
219points
99comments
#247of 4,366 in 2026
Top 6%of 2026 by points
How HN took it
CuriousMostly questions and neutral comments
7 positive, 20 neutral or asking, 3 mixed, 8 critical, out of 38 comments about the project. Thread score +0.03.
Idea: 4 for, 2 againstPrivacy: 0 for, 2 againstDocs: 0 for, 1 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Local-first design with memory as plain Markdown files
From 2 comments
I actually was using this quite a lot earlier this year, thanks for this! What I actually ended up doing was regularly pointing Claude at the Rowboat directory. Really useful to…
_puk on HNReally interesting, thanks for creating this. I've been slow to adopt the desktop apps (although use the web interface and VS code plugins for all the main players). This might…
QuicklyNow on HN
Vendor-agnostic option that works with many LLMs
From 2 comments
Really interesting, thanks for creating this. I've been slow to adopt the desktop apps (although use the web interface and VS code plugins for all the main players). This might…
QuicklyNow on HNThis looks really great! Quick question, is there any support for using local models?
nshotton on HN
Objections
Relies on cloud services for speech, TTS and search, so not fully local
From 2 comments
Rowboat markets itself as "local-first," but if you look in the actual codebase, transcription is Deepgram cloud, voice is ElevenLabs, analytics is PostHog, and the LLM is a…
piratebroadcast on HN1. No container to constrain a off-the-rails LLM. 2. Doesn't support generic IMAP email. 3. Doesn't accept my STT. 4. Doesn't accept my TTS. 5. Doesn't accept my SearxNG/custom…
nekusar on HN
Too many features; a simpler agent daemon is preferred
From 1 comment
All I want in an AI is this: 1. cd <myVeryImportantProject.repo> 2. start_AI_agent_REPL 3. "hey AI, analyze the code base in this repo, and find any and all bugs related to 'e.g.…
MomsAVoxell on HN
Gmail-only email connector; no generic IMAP
From 2 comments
Look really great! I'm a bit sad that the only way to connect to email is gmail. Is a generic IMAP connector on your roadmap?
dr_hooo on HN1. No container to constrain a off-the-rails LLM. 2. Doesn't support generic IMAP email. 3. Doesn't accept my STT. 4. Doesn't accept my TTS. 5. Doesn't accept my SearxNG/custom…
nekusar on HN
Lacks OS-level sandboxing for code
From 2 comments
1. No container to constrain a off-the-rails LLM. 2. Doesn't support generic IMAP email. 3. Doesn't accept my STT. 4. Doesn't accept my TTS. 5. Doesn't accept my SearxNG/custom…
nekusar on HNHow does sandboxing work for code? Is there a way to control the isolation myself, e.g. let it run code only in some VM that I provide? Edit: is there a sandbox for code?
thih9 on HN
Requests
Generic IMAP support
From 2 comments
Look really great! I'm a bit sad that the only way to connect to email is gmail. Is a generic IMAP connector on your roadmap?
dr_hooo on HN1. No container to constrain a off-the-rails LLM. 2. Doesn't support generic IMAP email. 3. Doesn't accept my STT. 4. Doesn't accept my TTS. 5. Doesn't accept my SearxNG/custom…
nekusar on HN
Native OpenCode support
From 1 comment
Would be more compelling to me if there was native support for Opencode
browningstreet on HN
Support for custom STT, TTS and search providers
From 1 comment
1. No container to constrain a off-the-rails LLM. 2. Doesn't support generic IMAP email. 3. Doesn't accept my STT. 4. Doesn't accept my TTS. 5. Doesn't accept my SearxNG/custom…
nekusar on HN
Multi-user group chat with shared steering
From 1 comment
What I'm looking for right now is a tool like this that lets more than one person participate in the conversation: right now Claude Code and similar tools are great for working…
dannyobrien on HN
Questions
Can it be used with local models?
From 1 comment
This looks really great! Quick question, is there any support for using local models?
nshotton on HN
How does code get sandboxed?
From 1 comment
How does sandboxing work for code? Is there a way to control the isolation myself, e.g. let it run code only in some VM that I provide? Edit: is there a sandbox for code?
thih9 on HN
Can it use Amazon Bedrock?
From 1 comment
Does this support using only private LLM instances? Does it integrate with Amazon Bedrock?
codexb on HN
Can it be used from mobile?
From 1 comment
Really interesting, thanks for creating this. I've been slow to adopt the desktop apps (although use the web interface and VS code plugins for all the main players). This might…
QuicklyNow on HN
Alternatives named
Claude Desktop and Claude Code
From 2 comments
Looks great. Is there an onboarding/xfer workflow from an existing Claude code harness? I’ve spent a ridiculous amount of time building my wiki, feature plans, retrospectives,…
starcalleryisss on HNI actually was using this quite a lot earlier this year, thanks for this! What I actually ended up doing was regularly pointing Claude at the Rowboat directory. Really useful to…
_puk on HN
Granola (meeting notes)
From 1 comment
I actually was using this quite a lot earlier this year, thanks for this! What I actually ended up doing was regularly pointing Claude at the Rowboat directory. Really useful to…
_puk on HN
Linzumi for shared AI sessions
From 1 comment
I use a tool called linzumi for this
binsquare on HN
Codex
From 1 comment
This is neat, excited to try it. Over the last months I’ve been exclusively using Codex for non-coding tasks. It’s not bad, but there’s much to improve. This seems like a step in…
sizero on HN