Personal AGI for the ambitious. Join our community: discord.gg/fqwAmDxa9

Pinned Tweet
Who wrote our YC? Prime did. One hotkey. No prompt. Let Prime complete you.
11
5
32
75,055
Who wrote our YC? Prime did. One hotkey. No prompt. Let Prime complete you.
11
5
32
75,055
Join the waitlist on Discord: discord.gg/fqwAmDxa9 Eventually, we will clone you. 8-second handoff is where it all begins.
5
529
Don’t prompt. Leave it to Prime. Today we’re introducing Prime : CUA that autocompletes your actions. Press a hot key and go get some coffee. Come back and see what Prime has done for you. Sign up for closed beta: discord.gg/fqwAmDxa9
6
1
22
10,167
Why are you still in the loop? Human-in-the-Loop is over. Clone-in-the-Loop is next.
6
4
958
Foundation models. World models. The User Model. The category is empty. We're going to define it. We're going to win it.
4
322
We were the bottleneck in our own loop. 14,000 lines shipped by Claude Code. 412 "yes"es typed by us. Same problem, every parallel-agent builder.
1
2
205
Language models got smarter. Humans got busier, not freer. Agents work faster than people — but they keep stopping. To ask. To clarify. To wait for review. The binding constraint stopped being model performance. It's human time and attention.
2
163
The bottleneck isn't the model. It's you.
2
123
AI-native builders run 5–10 agents in parallel. Models work at 200 tokens/sec. You answer at 0.3 questions/min. Guess who's the bottleneck.
3
243
Today, we publicly release HEVEC, a vector database built on homomorphic encryption, enabling end-to-end privacy with real-time search at scale. 💻 Code: lnkd.in/gTzWC_Bz 📄 Paper: lnkd.in/g45fEaFD
1
3
6
505
What HEVEC enables: • A secure, drop-in alternative to plaintext vector databases • End-to-end homomorphic encryption for both data and queries • Real-time encrypted search at scale (1M vectors in 187 ms)
1
2
5
316
As personal AI agents become deeply personalized, data ownership must belong to users. HEVEC enforces this through privacy-by-design architecture. 🙌 We’d love feedback from the AI, systems, and privacy communities.
2
5
304