News for hackers. Stuff that matters.

barqawiz

Show HN: IntelliChat minimalist, open-source UI for local and cloud AI

https://github.com/intelligentnode/IntelliChat

I built IntelliChat because I wanted a simple interface for working with different AI models, but without losing the advanced capabilities.You can generate text, images, and audio using local models, cloud models, or a mix of both.The goal is to keep the experience simple while still giving you the flexibility to choose how and where your models run.IntelliChat is completely open source and MIT...

( Read More... | no comments | 2 points | on HN )

Ask HN: Why my post is dead

I posted a link to a blog, but someone told me to is visible dead to them. Although the same post look normal to me.Can someone from hacker news team confirm if the post is dead: https://news.ycombinator.com/item?id=45953823

( Read More... | 1 comment | 2 points | on HN )
Re: on Monday November 17, 2025 @09:24AM (#45953824)
I explore why black-box prompts are risky in healthcare and how AI graphs offer a clearer path to safe and reliable medical support. The ideas come from the systems we’ve been developing at MedWrite to make clinical AI easier to trace and verify.
Re: on Monday June 30, 2025 @07:16AM (#44421856)
This PyData tutorial walks through building multi-agent AI systems using directed acyclic graphs to orchestrate NLP, vision, recommendation models, and any model.

Key sections:

- When to use multi-agent systems (6:37) - IntelliNode framework demo (9:35) - Hands-on labs with nutrition assistant (19:42) - MCP integration patterns (34:30)

Re:Platforms for Paid Open Source Issue Resolution? on Tuesday February 04, 2025 @08:45AM (#42932236)
Thanks toomuchtodo, this is helpful

Platforms for Paid Open Source Issue Resolution?

I'm looking for platforms (besides typical freelancing sites) where I can post complex GitHub issues requiring specific skills (LLM optimization in my case) and offer a financial reward for resolution.Any recommendations for platforms that attract top-tier open-source contributors?

( Read More... | 2 comments | on HN )

Show HN: Cama Pack – Moisture Monitoring for Raspberry Pi or Arduino

https://github.com/Barqawiz/iot_watering_system

Home based plant moisture monitoring solutions using Raspberry Pi and Arduino. We created several different dashboards including web hosted options and a custom cell phone application that connects to the Pi through Bluetooth.Everything is open source under the MIT license. Would love feedback, contributions!

( Read More... | 1 comment | 3 points | on HN )
Re:Notion AI-like Character with JavaScript – open-source on Monday October 28, 2024 @10:15AM (#41971227)
create a virtual character in JavaScript that give identity to your AI project.

Key Features: - Manual Mode: Control the character through on-screen buttons. - AI-Controlled: Connect with an AI assistant to enable automatic actions. - AI Characters: Customizable visual expressions and animations.

Github: https://github.com/Barqawiz/Tamagotchi

I added this as an issue here: https://github.com/Barqawiz/Tamagotchi/issues/5

Feel free to contribute.

Thank you for the suggestion! I’ll add an example in the README.

The character is rendered with JavaScript (no images), this enable the AI assistant to manipulate the animation directly.

Another approach is to use the pre-set button with different reactions, it can be given directly to the AI model through its tool functionality. commonly available in models like ChatGPT and Claude.

Show HN: Tamagotchi-Like Characters for AI Assistants – All in JavaScript

https://github.com/Barqawiz/Tamagotchi

I've developed a Tamagotchi-like virtual characters drawn in JavaScript. These characters can be manually controlled or interact dynamically with AI assistants, adding a visual identity and fun to AI.Imagine having an AI character that responds to user requests with different states, making interactions playful and engaging.Demo:...

( Read More... | 4 comments | on HN )
I'm happy to release some free IntelliNode keys for the Hacker News community.

Go to the app and click "Settings," then "Set One Key," and enter:

intelli-o21c27c218c0a750f440f

This will let you use the html simulator and other tools with GPT-4 Omni for free.

That's great suggestion, I can provide few prompts each for each IP.

Show HN: Try this HTML emulator with multiple LLMs, now better with GPT-4 omni

https://show.intellinode.ai/coder

I created this emulator to help with my work to generate and download HTML web pages from prompts. It accept editing on the same page to reach my desired screen and output javascript functional page.It worked well with the early LLM models, but now with GPT-4 omni as the backend it boosted the results and really adhere to my instructions .Let me know what you think, I'm also working on options...

( Read More... | 3 comments | 2 points | on HN )
The tsunami stones of Japan serve as a reminder of the timeless battle between human memory and nature's fury.
Re:There were no ancient computers and it's fine on Monday April 01, 2024 @08:47AM (#39893569)
An insightful take on the evolution of computing. should we also consider the device's ability to execute conditional operations?
Mini AGI can be created in two ways: one large model with a breakthrough that can take the current transformer to the next level. Or multi-models with different abilities that work to achieve user tasks and break into multiple steps.

The second option is more achievable in the short term, for this, I create a framework that uses graph theory to navigate the AI models as multiple tasks and handle the relations between different models.

This example shows how to create a data science teaching assistant using open-source Gemma and stable diffusion: https://www.kaggle.com/code/jaguar00/data-science-teaching-a...

This article describes the concept in detail: https://towardsdatascience.com/graph-theory-to-harmonize-mod...

Gemma is an open-source large language model (LLM) toolkit that allows you to customize pre-trained models for specific tasks. Use intellinode python module to fine tune the model and integrate with stable diffusion.
Re: on Wednesday February 21, 2024 @12:58PM (#39457158)
Integrating the capabilities of various AI models unlocks a symphony of potential use cases, but it is complicated when integrating different models providers and types like image, text.

I developed a python framework to orchestrate the AI models integration as a graph, read the article for more details.

To use this framework: pip install intelli

Older »