to your question i did a thorough benchmarking (hence late reply) used 18gb m3 pro macpro

full on-device with gemma 4 e2b is ~1.5s since last utterance. vad silence th is set to 600ms

now, when I connect local hermes agent that uses deepseek v4 flash via their api, latency jumps to 3.5s (this of course includes 600s of silence to even trigger pipeline)

btw, suggestions are throttled to one every 20s by default, it's configurable from the app

afaik cluely is waaaaay over 5s, but it makes sense because their users need lots of ai reasoning to answer interview qs :D different target audience then stagewhisper

About me: my name is Piotr. I'm having plenty of calls as a freelancing programmer, and have interest in audio domain, so it was natural for me to pick this as my side project. I struggled a bit with echo cancellation, and writing idiomatic plugins to let users use their OpenClaw or Hermes agents as BYO AI (basically backend). I started project coding Tauri app by hand, only after establishing architecture I started leaning on AI coding agents. I use Claude Code with https://github.com/openai/codex-plugin-cc for "adversarial-reviews".

On the website I've included an offer to upgrade StageWhisper Lite to Founders edition with one-time payment: this give screen reading (via accessibility tree) and proactive, two-way communication - that is, your connected agent can provide suggestions by listening to audio (Cluely style), and you can chat with it during the call. Again, you bring your own AI, so Founders is a single payment, no subscription offer.

Both apps include MCP and in-app chat with your transcripts and meeting notes. Both also allow to connect any model downloaded from HF or connecting OpenClaw/Hermes.

I created StageWhisper Lite & Founders to test business feasibility of one-time payment AI apps that have no marginal costs (you either use local model or your own assistant).

I hope you will enjoy free Lite app and consider upgrading to Founders.

Comments URL: https://news.ycombinator.com/item?id=48904884

Points: 3

# Comments: 3

The biggest unlock was wiring it up to my agency's whatsapp group - it's now basically a multiplayer chatgpt. Not a "personal" assistant, but more of agency's assistant. It can send ad hoc mails to our clients when asked, but also tells jokes when atmosphere is tense.

Each day it checks it's own inbox and once a week it sends me a kind of social listening report, but those are kind of workflows easily reproducible elsewhere.

I'm actually so bullish on the potential of openclaw kind of software I've built a desktop app for it, stagewhisper.io.

It's like a Granola for your OpenClaw. It listens to your system audio, records your screen (all data stays on your computer) and asks your assistant for suggestions or creates a tasks. Example: client asks for referrals during a call, StageWhisper.io picks it up and asks OpenClaw to send email with case studies.

It's absurdly fun to use, mainly because the delay between when the task pops up and the work starts is approaching zero.

still hosted on private GH: https://github.com/PiotrAleksander/open-notebook-mcp We will probably soon merge it to the main repo

I thought I hack around. App consists of:

- users write Markdown, LLM turns it into interactive MDX post

- MDX with generated widgets is rendered in e2b sandbox

- generation & publishing (sanitization, etc) pipelines run on Inngest (their docs won me over Temporal)

Would it make sense to go mobile first and focus on ‘interactive micro-blogging’ (Twitter with widgets)?

Comments URL: https://news.ycombinator.com/item?id=45029034

Points: 1

# Comments: 2

https://worrydream.com/ExplorableExplanations/

https://www.inkandswitch.com/potluck/

https://news.ycombinator.com/item?id=43773813

I’m building a publishing stack for “vibe blogging”, think Bolt.new x Substack. It consists of:

Authoring - users write Markdown, LLM turns it into interactive MDX post

Sandboxing - MDX with generated widgets is rendered in e2b sandbox

Pipelines - generation & publishing (sanitization, etc) pipelines run on Inngest (their docs won me over Temporal)

Distribution - via subdomain/paid custom domain. Stripped version of the post for repurpose as a newsletter (Inngest Workflows)

I’d love feedback on:

1. Does it make sense to go mobile first and focus on ‘interactive micro-blogging’ (Twitter with widgets)?

2. I consider launching in price sensitive, but creator-rich markets like India, Brazil and Mexico to build momentum. Anybody has experience with that?

All thoughts welcome!

Comments URL: https://news.ycombinator.com/item?id=44644021

Points: 1

# Comments: 1

I’m building a publishing stack for “vibe blogging”, think Bolt.new x Substack. It consists of:

Authoring - users write Markdown, LLM turns it into interactive MDX post

Sandboxing - MDX with generated widgets is rendered in e2b sandbox

Pipelines - generation & publishing (sanitization, etc) pipelines run on Inngest (their docs won me over Temporal)

Distribution - via subdomain/paid custom domain. Stripped version of the post for repurpose as a newsletter (Inngest Workflows)

I’d love feedback on:

1. Does it make sense to go mobile first and focus on ‘interactive micro-blogging’ (Twitter with widgets)?

2. I consider launching in price sensitive, but creator-rich markets like India, Brazil and Mexico to build momentum. Anybody has experience with that?

All thoughts welcome!

Comments URL: https://news.ycombinator.com/item?id=44595455

Points: 3

# Comments: 1

One thing that would hold me back from migrating is https://www.inngest.com/docs/guides/user-defined-workflows - thanks to which my users could quickly add automations (like sending newsletter announcing new blogpost)

https://worrydream.com/ExplorableExplanations/

https://www.inkandswitch.com/potluck/

https://koomen.dev/essays/horseless-carriages/

I’m building a publishing stack for “vibe blogging”, think Bolt.new x Substack. It consists of:

Authoring: users write Markdown, LLM turns it into interactive MDX post

Sandboxing: MDX with generated widgets is rendered in e2b sandbox

Pipelines: generation & publishing (sanitization, etc) pipelines run on Inngest (their docs won me over Temporal)

Distribution: via subdomain/paid custom domain. Stripped version of the post for repurpose as a newsletter (Inngest Workflows)

Demo is nearly ready, I’ll launch it on Show HN and share it with waitlist subscribers soon.

I’d love feedback on:

1. Does it make sense to go mobile first and focus on ‘interactive micro-blogging’ (Twitter with widgets)?

2. I consider launching in price sensitive, but creator-rich markets like India, Brazil and Mexico to build momentum. Anybody has experience with that?

All thoughts welcome!

Comments URL: https://news.ycombinator.com/item?id=44442003

Points: 2

# Comments: 4

Waitlist is open, /blog contains example posts