We raised $5.5M to build Beacon. Yesterday, it hit #1 on Product Hunt.

Hey everyone! We recently announced Asymptote Labs' $5.5M seed round and launched Beacon, our open-source, self-improving memory for AI coding agents.

Yesterday, Beacon also hit #1 Product of the Day on Product Hunt! 🚀

We're entering a world where AI agents will vastly outnumber human employees, but we're still missing the infrastructure to see and control what they're doing.

Agents are writing code, executing commands, accessing sensitive data, and making decisions autonomously. Yet most organizations have little visibility into what their agents are actually doing, let alone the ability to govern their behavior or respond when something goes wrong.

The challenge isn't just making AI agents smarter. It's making them observable, accountable, and safe to operate at scale.

That's what we're building at Asymptote Labs: the visibility and control layer for AI agents, wherever they run.

And we're starting with Beacon, our open-source foundation for understanding agent activity.

Beacon helps developers:

• Self-improving memory: Turn past debugging sessions into reusable skills.

• Cross-agent learning: Share knowledge across Claude Code, Cursor, Codex, and 20+ coding agents.

• Session search: Search and replay past sessions instead of rediscovering solutions.

• Security intelligence: Identify risky agent behavior and get actionable recommendations.

Beacon is free, open source, and local-first.

We've already crossed 3,200 GitHub stars, and we're just getting started!

Huge thanks to our investors and everyone who's supported us along the way.

• Read about our fundraise: https://asymptotelabs.ai/blog/asymptote-labs-raises-5-5m-seed-round

• Check out Beacon: https://github.com/Asymptote-Labs/agent-beacon

If you're building with AI agents, we'd love to connect and hear your feedback!