Elly Lin

Product Manager | Builder | Creator

[Elly Lin @ieattoomunch]

@dmitry is teaching about #hermes agent right now if anyone wants to join! 11-12pm PT. https://t.co/049sMOzngZ
@buildwithRemy

[Remy @buildwithRemy]

We helped bring a room of incredible women (engineers, builders, aspiring founders, CEOs) today to overcome AI anxieties for #nytechweek 🩷

We shared stories and inspired each other to build over cocktails. Many were excited to prompt full stack applications with Remy 🙂‍↕️

We love @womeninaisf & @WomenDefiningAI ✨

[Elly Lin @ieattoomunch]

@skygodkingdom 😎😎

[Sky Yang @skygodkingdom]

Come race Porsche 911s with us at Pier 30 this saturday.

1000+ founders raised more than $1M+. Three 911s. A racing track we're building from scratch on the San Francisco waterfront. Open bar. DJs. Food trucks. The whole thing.

We're turning Pier 30 into an F1-style party.

Saturday June 6th. 1:30-6 PM. Pier 32 at the Embarcadero.

RSVP approval required. Driving slots are limited.

Organized by @imagineagi

with @fondohq, @TrustVanta , @awsstartups, @rippling, @composio, @conduitai, @hyperspell, @cladlabs, @getreflex, @mindstudioai, @joinergo, @EntelligenceAI. @PlanetScale

Link below 👇

[Elly Lin @ieattoomunch]

@dmitry @Lovable @Replit you’re really missing out if you haven’t tried it 😵‍💫

[Dmitry Shapiro @dmitry]

If you're using @Lovable or @Replit would really love your thoughts on Remy, our new product builder agent 👇

[Elly Lin @ieattoomunch]

@garryslist omfg 😭🥺

[Elly Lin @ieattoomunch]

pls like so I can get a meeting with @andrewchen 🥹

Hi Andrew! This is from last year @ SF tech week. I’m a fan & have a signed copy of your book “cold start problem”. 😍

I’m working on an incredible AI platform for builders that enables building a whole startup in hours!

[Remy @buildwithRemy]

Most people will sit on their ideas this weekend.

You’re probably here because you don’t.

The Remy Hackathon (May 1–3) is a virtual, async weekend to turn an idea into a real product — backend, frontend, database — without writing code.

Join hundreds of builders (Meta, EY, Oracle + more). $5,000+ in prizes.

After this weekend, you could have something real.

Tune in for opening night tomorrow ↓
https://t.co/xvp76RViLg

[Elly Lin @ieattoomunch]

@mindstudioai damn that’s crazy

[Remy @buildwithRemy]

Remy just built a full 360° equirectangular panorama app, from just one prompt

"Use a frontend 360 viewer to display a gallery of equirectangular panoramas you can switch between, using the GPT-Image-2 model."

[Elly Lin @ieattoomunch]

@Dakshay 👏 👏 👏

[Dakshay Mehta @Dakshay]

We built Lore.

An agent harness with a memory system designed for learning. It creates nodes and connections as you use it, which is where the name comes from. Knowledge through experience.

A lot of the memory design came from @karpathy's LLM wiki posts. Lore's memory is essentially a local wiki that scales and compounds the more you use it. The system learns you while you learn with it. (https://t.co/9OexFlK7VN)

The UX angle came from @FarzaTV's Clicky launch. Seeing Cursor companion helped us figure out how to fit an agent harness into something you'd actually use every day, and have less friction. We already had the agentic backend from building Talking Books (still building that). We just needed the right perspective on the use case to port it locally. Thanks Farza.

Running a voice assistant usually means TTS costs stack up fast. So we run a local TTS model on Mac, plus local OCR and Apple's FastVLM for vision. Better accuracy, lower first-token latency, no cloud bill.

And you can also enable Local inference through just running @ollama and it will autodetect the model and use that instead. So you can technically use Lore without wifi.

In this demo we're reading some amazing work from @googleresearch on TurboQuant. I love this paper @demishassabis @OfficialLoganK.

1. Tutor
2. Research
3. Learn
4. Reading
5. Agent (computer use + OpenClaw + self-healing local memory)
6. Transcribe (basically Wispr Flow, because why not)

Next up is persistent long-term memory. @garrytan's Gbrain is helping us get there. That OS is epic.

This feels like a new way to learn, read, and do. A lot of dots had to connect to get here, and more are still connecting. Excited to put this in people's hands.

[Elly Lin @ieattoomunch]

@AgentOpusAI ADS

[Agent Opus @AgentOpusAI]

Rewatch this and count the tools it would've taken anywhere else.

Character lock. Product lock. Logo lock. Style lock. One prompt.

From Creative → Creator, for real.

First 100 to RT + comment "ADS" get DM'd credits to try it 👇

[Elly Lin @ieattoomunch]

we really want to collab so to support MoltBot, we created a 40% off our subscriptions until 2/1 😃 https://t.co/LmOQ56KOO1

[Elly Lin @ieattoomunch]

@steipete Thank you for listing Synthetic as a #Clawdbot provider :) We are 3 people team & would love to collaborate with you, please DM me!
We're a privacy-first, open-source model platform. We have high rate limits, support most open source models, & don't quantize.

[Elly Lin @ieattoomunch]

If anyone wants a referral code, here's $10-20 off! https://t.co/CTTUUlUxTT

[Elly Lin @ieattoomunch]

@Angaisb_ @buildlastic Would you ever give https://t.co/KuMwdyx0Ds a try? :) privacy-first platform for open-source models, where a $20/mo subscription gives 3x higher rate limits than Claude

[Elly Lin @ieattoomunch]

@BijanTavassoli @SkylerMiao7 check out https://t.co/f8E0uk0kAL ! they run open-weight models directly, super fast, with full privacy 😎