Hacker Newsnew | past | comments | ask | show | jobs | submit | mikerubini's commentslogin

That's the exact use case we're targeting! Once you start giving AI more autonomy in your projects, sandboxing becomes critical. Lots of people are vibe coding in prod these days


Hey HN! Founder here.

Built Cognitora.dev after getting frustrated with existing AI coding environments being either too limited, too heavy or too expensive. We're using Kata containers with the flexibility to run on either Firecracker or Cloud Hypervisor - letting us optimize for the best performance per workload.

Key differentiators from e2b/Daytona:

- True isolation with hardware-level security (not just Docker) - Sub-3s cold starts vs 10-30s elsewhere - Kata flexibility: Firecracker for ultra-fast startup, Cloud HV for heavier workloads - Built-in AI context preservation across sessions - Works with any LLM/model (not locked to specific providers)

The sandbox handles everything from simple scripts to full deployments. We're seeing devs use it for prototyping, code review with AI, and even production debugging in isolated environments.

Still early but would love feedback from the community.

Website: cognitora.dev

Docs: https://www.cognitora.dev/docs/getting-started/examples


> Sub-3s cold starts vs 10-30s elsewhere

What do you mean? I have been using e2b and daytona for the past year and they never took that long to boot. It usually takes less than 1 second for sandboxes to come live


Hey, yeah I respect your opinion, of course!

That's why in the beginning of the call it discloses it's an AI. Not all people are cool with it, but for most people who are not into tech, it's actually a fun experience I would argue


I built a new software product that does fully automated, live product demos with AI agents. They share their screen and basically replace sales reps demoing the product.

I mainly use Google Meet's API (hosting the meeting), OpenAI GPT v4o (llm), 11labs (for voice), deepgram (for the transcription of the meeting) and Twilio (to connect to the meeting).

Of course, it's early days (I built this yesterday) but so far, the results looks promising.

Unlike pre-recorded demo videos, AI agents can screenshare and demo the product while also responding in real time to questions and handle objections as they arise.

What do you think?


Founder here

Thank you for posting my thread!

Feel free to ask questions on this =)


Hey HN,

I made a new SaaS over the last 3 days: https://whalepeek.com

You can shadow top NFT collectors and get alerted when they buy, sell or mint a new NFT.

Heavily inspired by eToro commercials that popped up all over Youtube: "copy what top traders do" - Here you can copy what other NFT influencers are doing.

A big problem in doing that has been detecting fake transactions. A lot of scammy creators are airdropping NFTs into influencers' wallet. We detect fake mints, fake buys and fake sales - and only notify you of real ones.

Technically, the project is built in PHP + mysql and some JS for the charts. Hope you like it!


Have you made any money flipping NFTs?


So far, we have 500+


Let’s make that 1,000+ now


Hey Hacker News,

Yesterday I made https://JobScout.co

It’s a remote job board that takes job opportunities out of Facebook.

Why make yet another remote job board? The market seems saturated at this point.

Here are some considerations on why I decided to make this product a reality:

I feel everybody is either copying Pieter Levels who owns remoteok.com, or using his API. This results in 100s of job boards promoting the same jobs, which then results in more applicants for the employer, but more competition for applicants.

With JobScout, I wanted to exploit a different source, Facebook, in order to get different kinds of jobs, which usually don’t get as much love and that you wouldn’t find on other remote job boards.

Feedback welcome


how do u scrape FB?


I'm a data collection expert with 10+ years of experience


""


mike@rubini.solutions


Thanks, go it. You can delete now


No worries, my email is public anyway


Discovering rising trends at https://treendly.com


Hey Hacker News,

Problem: I often hear someone on one podcast and want more, but there's not an easy way to find them elsewhere.

Until now.

Podda allows you to search podcasts by guest, and also receive a notification whenever a person you like gets on a new podcast.

I just coded this today in ~5 hours, and all feedback is welcome.

Question: right now I only list episodes a guest appeared on. Should I also list podcasts that a guest hosts?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: