We're looking to more than double our founding team at @beacon.sh, hiring aggressively across research and engineering.
We're building the visibility and control layer for AI agents, and we've got some serious momentum:
$5.5M raised in seed funding
3,200+ GitHub stars and a growing OSS community
#1 Product of the Day on Product Hunt
Our founding team brings experience from Doppel, Brex, and Trail of Bits, and we're looking for exceptional builders to join us.
We're hiring:
Founding Engineer: Build high-performance infrastructure to secure and govern AI agents at scale.
Founding Security Researcher: Break AI agents, uncover novel attack surfaces, and publish cutting-edge research.
Who we're looking for:
Deep technical curiosity and obsession with craft
High agency, relentless ownership, and bias toward shipping
Exceptional problem solvers with incredibly high standards
We want world-class engineers and researchers. We don't care about pedigree. We care about what you've built, the problems you've solved, and the quality of your work.
NYC in-person preferred, open to exceptional remote talent.
DMs open. Come build with us! Contact me at founders[at]asymptotelabs.ai
This is like AI agents having Apple Continuity. Very cool.
Que: how do you handle the artifacts across agents?
@5harath We normalize all AI telemetry (and extend OpenTelemetry's genAI standard) into a standard data model across 20+ harnesses! This is what enables us to show you all your AI activity in one place + make your context + memories portable across harnesses! More on our coverage here: https://github.com/Asymptote-Labs/agent-beacon/tree/main#supported-agents
love it - could be your tagline @justindsouza
are api keys that show up in command output scrubbed before a session turns into a memory?
@bbueno Yes, secrets are fully redacted (especially if you're using Beacon Cloud). See our redaction practices + security posture here: https://docs.beacon.sh/security/retention-redaction#retention-and-redaction
We're also fully open-source so you can inspect the code yourself! Check it out and I'd love to hear your feedback: https://github.com/Asymptote-Labs/agent-beacon
@justindsouza ah ok, good to know, thanks Justin
@bbueno no problem!
@justindsouza @bbueno anything else @beacon.sh should build/improve/fix from your perspective?
Does Beacon keep the memory local, or sync it to a cloud account?
@modiyilreji Hey Reji! We have 2 modes: local-only (no data leaves your machine), and Beacon Cloud (your agent session data is synced to your cloud account. With Beacon Cloud, the main value add we're giving users is 1) continuously generating findings + skill opportunities for your sessions, and 2) no infra overhead for you to think about. With Beacon Cloud you can also choose different redaction modes (metadata-only or full agent traces).
I'd love your feedback on Beacon :) Definitely check out our repo and if you like it please give us a star! https://github.com/Asymptote-Labs/agent-beacon
@justindsouza Thanks, Justin. Local-only mode is good to have.
@modiyilreji Glad to hear! Try it out and let me know what you think :)
@modiyilreji @justindsouza yes, and make sure to add your review here! producthunt.com/products/asymptotelabs/reviews
@modiyilreji good q! icymi @justindsouza recorded a live demo here. hope it clarifies
Does it ever save the wrong context and bring it back later when you don’t actually need it?
Congrats @justindsouza & team!
Thanks for sharing @fmerian :)
@fmerian @hamza_afzal_butt really great question Hamza! This is candidly one of the hardest problems we've seen as we've built out Beacon. We have a configurable human-in-the-loop step so that you can approve any reusable memory + skill candidates that are generated. In addition to that, we leverage your agent sessions as a feedback loop to actually evaluate whether those approved memories + skills are used at runtime.
Would love your feedback on Beacon if you check it out! https://github.com/Asymptote-Labs/agent-beacon
@justindsouza @hamza_afzal_butt is a legend. thanks for the continuous support!
The portability is the bit I keep thinking about. Most sessions end with one useful lesson that's tied to a specific harness — a Claude Code quirk, a Cursor setting — and another that's true for the whole codebase. When a memory like that gets carried into a different agent, does Beacon tag or filter it by where it came from, or does everything travel as-is? I'd worry a harness-specific trick could read as a general rule in the wrong context.
@jcbuilds For coding session portability, we actually have a primitive for this called session handoffs! On the memory side, we tie Beacon-generated memories and skills to the specific agent session(s) they came from. There's also a configurable human-in-the-loop step so you can approve them.
Once they're persisted, Beacon continuously uses your agent session traces as a feedback loop to understand how those skills + memories are being used at runtime, so we can proactively surface to you whether you're getting value from them or not! Check it out and I'd love to get your feedback: https://beacon.sh/
@jcbuilds appreciate your support! help us spread the word on X, repost this
What happens to a saved workaround when a repo change makes it obsolete? That seems like the tricky part of carrying lessons between sessions.
@oleksii_sekundant Great question Oleksii! This is definitely one of the hardest problems we're tackling. Beacon uses traces from subsequent sessions as a feedback loop to see whether a saved workaround still works. As the repo evolves, we can detect when that knowledge becomes stale and update or retire it.
I'd love your feedback on our approach. Please check out our open-source project and let me know what you think (don't forget to star)! github.com/Asymptote-Labs/agent-beacon
@oleksii_sekundant @justindsouza anything else @beacon.sh should build/improve/fix from your perspective?
The portability angle is the part that hits home for me — I switch between Claude Code and Cursor in the same day, and right now the second tool starts from zero no matter what the first one figured out. Turning past sessions into reusable skills instead of another summary doc is the right shape for that. One thing I'm curious about: are those memories scoped per repo by default? A workaround that makes sense in one codebase could be actively wrong in another, so I'd want the compounding layer to know which project a lesson came from.
@jcbuilds The scoping is really up to you and dependent on your codebase layout :) You can choose where to persist the memories + skills that Beacon generates for you, and can either share across repos or scope per repo.
Definitely try it out and let me know what you think JC! I'd love to get your feedback on the product: https://github.com/Asymptote-Labs/agent-beacon
@jcbuilds @justindsouza also make sure to claim your @beacon.sh profile to see where you stack up on the leaderboard: beacon.sh ✌️
@jcbuilds @fmerian here's the link to our profile leaderboard btw! https://beacon.sh/leaderboard