

✓helping govts accelerate | @Replit | @usnavy veteran 🇺🇸





1. Give Replit a mission like "Make numpy 19x faster" 2. Swarm of agents will work until mission completed 3. numpy is 19x faster First harness for starting swarms of cloud agents

The vision of Replit is the vision that always comes true You need to try Replit Missions right now

Michele, as always, is ahead of the curve and sees around the corner. Everything that matters will have a scaling law, and agent swarms is no different. I think this is also where most safety and steer ability challenge come from too! Many many many problems to solve

7 years of living and breathing the Bitter Lesson 🫡 We have so much fun ahead of us. Scaling is the gift that keeps on giving.


Incredible new product by @Replit. The idea that I can just send an AI agent to go take care of things and handle all those things with the right boundaries in place, so that I don't need to worry about all the little minutiae: this is how businesses become a self-driving company.

I've been Mission maxxing over the last couple of weeks, I've had multiple notable achievements. My favorite was adding support of all web APIs in our durable programmatic tool calling sandbox ("codemode") for agents to leverage, barely took any of my time.



How scaling agent swarms can optimize software performance.


LLMs have gotten more autonomous recently but when you give them a goal they often misunderstand you, work aimlessly, and waste your tokens. Today, we’re introducing Missions—the world’s first agentic swarm harness that can accomplish any goal you give them within set budget. Try it today with something like “get me my first 10 customers:” replit.com/blog/introducing-…