AI YC interview with Gstack agents

the local-brain / no audio leaving the laptop detail is what would actually get this past a company's security review, most tools in this space cannot say that honestly. curious about the live-meeting etiquette side though - when a persona jumps in to critique the shared screen out loud, how does it know not to talk over an actual human who started speaking at the same moment. is there a turn-taking signal or does it just wait for a pause

The local brain running on your own machine is the detail that actually matters here — most meeting AI tools quietly route everything through their infrastructure and call it 'private.' The open MIT license on the personas is a nice architectural choice too. The part I'd dig into as a developer is the AgentCall API: when I bring my own agent into a call, does it receive raw transcript chunks in real time, or does gstack buffer and parse before the agent sees anything? The latency and chunk boundary design determines whether a custom agent can stay coherent during a fast conversation.

Having agents critique a shared screen in real time is a strong idea. Can each persona retain context across multiple meetings, or does every call start fresh?

Cool stuff 🚀, Don't know how you pulled this off but getting gstack agents to join meetings is like a major upgrade to @garrytan 's gstack. Even though i was stuck in the shared queue for some moment, i still had it running using my own claude code as brain, Had a call with the gstack CEO and I'm already loving it. 😄

Hey all 👋Quick update: we’re seeing heavy usage and the shared brain pool is currently at capacity. For now, please clone the repo, create your own brain, and run it locally. Also, this is a self-learning agent. If you run into problems, just ask it to resolve them and it will work on fixing them.

Maker here 👋 I built gstack to answer one question: what does a meeting feel like when AI agents are participants, not notetakers?

So they join your Google Meet as voice bots. The YC-partner persona opens with "what are you working on, and who actually wants it?" — and honestly it's uncomfortable in the best way. Share your screen and the senior-designer persona scores your page out loud, then posts the points to chat.

Three things I care about:
1. Honest open source — the whole platform is MIT (github.com/pattern-ai-labs/gstack-joins-meeting), and the personas are Garry Tan's, credited and MIT.
2. The "brain" is YOUR coding-agent session (Claude Code / Cursor / Codex) on your own laptop — no audio or files leave your machine, just transcripts, only for calls you start.
3. gstack is really a demo of AgentCall (agentcall.dev) — the API that lets any agent take a seat in a meeting. If you build agents, you can put yours in a call too.

Try it free, no card: gstack-meeting.com. I'll be here all day — would love your feedback.