OpenClaw is the fastest-growing open source project, but there are no stories of running it safely in production at scale. As we started deploying agents internally at @brexHQ, we couldn’t stop thinking about this question.
Agents work, but nobody wants to give them real credentials. Instead of waiting for a solution to emerge, we decided to try a novel approach: using LLMs to judge the network traffic of an AI agent.
Today we’re announcing CrabTrap, an open-source proxy that intercepts every outbound request and blocks risky activity using LLMs, before it ever hits an external API. The results are promising; we believe it’s a meaningful step forward in the security of agent harnesses in production environments.
Try it out today.
(As a side note, it was really fun to work personally on a real systems problem again. And btw, if you want to work at a place where the CEO is building proxies at night, we’re hiring!)
Losing half a century's worth of nuclear progress and proliferation to Greenpeace hippie hysteria will haunt the west (and the world) for a long time to come.
My sleep scores during recent travel were in the 90s. Now back in SF I am consistently back down to 70s, 80s.
I am increasingly convinced that this is due to traffic noise from a nearby road/intersection where I live - every ~10min, a car, truck, bus, or motorcycle with a very loud engine passes by (some are 10X louder than others). In the later less deep stages of sleep, it is much easier to wake and then much harder to go back to sleep.
More generally I think noise pollution (esp early hours) come at a huge societal cost that is not correctly accounted for. E.g. I wouldn't be too surprised if a single motorcycle riding through a neighborhood at 6am creates millions of dollars in damages in the form of hundreds - thousands of people who are more groggy, more moody, less creative, less energetic for the whole day, and more sick in the long term (cardiovascular, metabolic, cognitive). And I think that many people, like me, might not be aware that this happening for a long time because 1) they don't measure their sleep carefully, and 2) your brain isn't fully conscious when waking and isn't able to make a lasting note / association in that state. I really wish future versions of Whoop (or Oura or etc.) would explicitly track and correlate noise to sleep, and raise this to the population.
It's not just traffic, e.g. in SF, as a I recently found out, it is ok by law to begin arbitrarily loud road work or construction starting 7am. Same for leaf blowers and a number of other ways of getting up to 100dB.
I ran a few Deep Research sessions and a number of studies that have tried to isolate noise and show depressing outcomes for cohorts of people who sleep in noisy environments, with increased risk across all of mental health (e.g. depression, bipolar disorders, Alzheimer's incidence) but also a lot more broadly, e.g. cardiovascular disease, diabetes.
Anyway, it took me a while to notice and after (unsuccessfully) trying a number of mitigations I am moving somewhere quiet. But from what I've seen this is a major public health issue with little awareness and with incorrect accounting by the government.
@VictorPontis Very insightful to see how you've approached team's growth and product focus. Feeling energized same way after four years speaks - inspiring to witness the craft behind luma. Congrats!
Today we’re announcing our 24’ Summer release at @BrexHQ! ☀️ AI-powered accounting with continuous close (first software ever to do so), two completely redesigned products, and a blazing-fast new UI with 100+ improvements that make Brex the most powerful *and* simple it’s ever been
Six years ago, we started Brex as a corporate card designed by a tech company, not a bank. We grew quickly along with our customers, and built so many products as they scaled – like global capabilities, robust expense policies, live budgets and more. Our product depth is why 120+ public companies rely on Brex every day to run their businesses.
But back in December, we decided to look inward. We realized that building so much, so quickly, sometimes came at odds with our original vision of simplicity. We made our main priority for this year to deliver not just the most powerful spend platform on the planet, but also the most simple, thoughtful and delightful user experience for founders and Finance teams.
We had to completely change how we run the company to make this release happen and I’m so proud to share it with you–as it’s our largest and most polished release to date. Key highlights:
📕 A new AI-based accounting workflow that allows customers to achieve continuous close and close the books every day – the nirvana of accounting.
💳 A new Card Control Center that makes it easy to manage cards and limits at scale (whether you have 5 or 50,000 cards), as well as spend requests that replace janky PO workflows.
💵 Bill Pay with AI-based line itemization, multi-entity support, and the ability to pay bills by card, earning rewards and cashback on spend that was previously going through ACH.
🔎 Redesigned tables, with consistent and blazing-fast responsiveness on filtering, pagination, grouping, sorting, as well as LLM-based search that is 400% faster.
🚀 100+ other updates, such as AI-powered Slack integration, account co-branding, audit trails, sandbox mode, stable credit limits, a new security hub and much more.