News for hackers. Stuff that matters.

realtimex

by private AI - can I run it on my own computer?
Re:Ask HN: Any example of successful vibe-coded product? on Tuesday December 30, 2025 @10:17PM (#46440892)
I build a full-featured CRM built with React, shadcn/ui, and Supabase. vibe code in Antigravity + CC ($20/month) + Gemini free

https://github.com/therealtimex/realtimex-crm

Re:Show HN: OpenAI hasn't released their Apps SDK so we did on Friday October 10, 2025 @05:53PM (#45544224)
+1 star. Super easy to add ui-rich widgets to chat. It took me 5 minutes to add weather widget to realtimex.ai

Show HN: RealTimeX – Local‑first private AI agents

https://realtimex.ai

Hi HN — we’re building RealTimeX, a way to run private, always‑on AI agents with a local‑first approach. The core idea: minimize cost by running models on your own machine (or office server) and only call out to cloud when you explicitly choose to. That also keeps more data in your control.Why we built it?Cloud‑only AI can mean unpredictable spend, tail latency, and privacy headaches. Consumer...

( Read More... | no comments | on HN )
Delivering a smooth experience in receipt processing is surprisingly complex. There are numerous factors to consider, such as:

- Multiple languages: Handling receipts in various languages like English, French, Spanish, Chinese, etc.

- Multiple currencies: Processing receipts from different countries with various currencies.

- Multiple file formats: Managing receipts in diverse formats (PDF, images, etc.).

Despite these challenges, Keepy's pricing is just a small fraction of what manual data entry would cost.

Are you referring to the pricing?

Show HN: Keepy AI – Automate Receipt Data Entry with an Email

https://keepy.us/

I moved to the Bay Area to dive headfirst into the GenAI wave, eager to learn how startups build AI. I co-founded a startup with a friend and quickly realized a familiar pain: managing receipts. I'd "keep" them in my pocket, on a table, in the car – and told myself I would manage it later. Later never came.Talking to friends, I realized this was a universal struggle. That's how Keepy was...

( Read More... | 3 comments | on HN )
Re:Ask HN: What have you built with LLMs? on Tuesday February 06, 2024 @05:54PM (#39282011)
We build https://aichat.realtimex.co, a customer support AI working along side Human Agents. It's a RAG system with embeddings built from crawling pages of the website and user-uploaded documents including dynamic databases (such as products and pricing). The key difference with other LLM's CS products is the collaboration between the AI Agents and Human Agents. We are inspired by aircraft's pilots and autopilots collaboration. In this case, the AI and Human Agents silently collaborate to bring the best support to customers.