mikerubini
Joined 9 years ago
Karma
205
Submissions
143
Member since
Jul 2
Entrepreneur and musician. Jazz lover. Padel addicted. I make SaaS products at https://flatnine.co
View on Hacker NewsRecent submissions
Comment · 1 year ago
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
Comment · 1 year ago
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
Comment · 2 years ago
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
Comment · 2 years ago
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?
Comment · 4 years ago
Founder here
Thank you for posting my thread!
Feel free to ask questions on this =)
Comment · 4 years ago
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!