HardwareAssistant

7h 0m

by srinivasagudi0

Jarvis Hardware Builder is a hardware planning assistant with a CLI, a Streamlit UI, structured project memory, revision history, file attachments, and exportable project plans. I plan to add moore in future if possible. Features Builds hardware plans from structured project inputs Ask follow-up questions against saved project context Save projects in SQLite with revisions, tags, and attachments Export projects as JSON, Markdown, and PDF Fall back to a local plan generator when no OpenAI API key is available A good UI for easier workflow and asthetics.

🎫 Golden ticket winner!

sundial.city

10h 26m

by bunnyguy

my personal website (originally submitted for Page) OK take two electric boogaloo. New updates include: new about/art/portfolio page. Basicaly anything that wasn't the index page or blog page is new

🎫 Golden ticket winner!

Voyago -- AI-assisted travel agent proof-of-concept

26h 29m

by Harry

PSA: If you're looking for demos to see all parts of project, please reference the demo hub here! I was asked to include only the main app as the demo link. https://docs.google.com/document/d/1ATQCNs4iA9GmtCfzy3Zy8waQqAyNNWDVDrxhREHo9P4/edit?usp=sharing What is this? For now: A multi-agent system that learns your restaurant preferences through doomscrolling, and recommends you more restaurants! (+ the data extraction pipeline needed to collect the dataset it needs) In the future: A more agent-oriented agenetic system that will learn not only on restaurants, but about your opinion on certain attractions, attendable events, etc via doomscrolling. It will then help you build a trip itinerary by recommending you places / events you may enjoy. What it does (currently): 1. You tell Voyago where you’re staying at / your location (limited to Vancouver for now) 2. Voyago gives you a list of restaurants, presented in a reels-like format. It tells you the following things for every restaurant: - Genre (cuisine type) - Price range for full meal - Address - Operating hours - Top tags associated with the restaurant - The rough route + estimated time for you to either walk or drive there 3. For every restaurant, you can read the description and rate it out of 10 based on how much you like it 4. As you rate more and more, Voyago will use the numerical input you give to weigh which tags you like and which ones you do not. 5. Once enough tags are accumulated, the LLM will occasionally generate a summary of your preferences 6. Voyago will gradually reduce the likelihood of restaurants containing tags that already have very strong pro / anti signals, and vice versa for those with tags that are not frequently rated. 7. As you scroll, you can click "AI recommendation" button on the left side panel to let the agent pick out restaurants that you may enjoy, according to what Voyago has learned about your preferences Background The problem with planning a trip these days is that when you search up “things to do / eat in Vancouver”, it is always the same things that rise to the surface of your search engine. In reality, as a Vancouver resident myself, I can confirm that I’ve had far richer experiences at places which are hardly reachable by search engine unless if you dig vigorously. This is a problem because it demonstrates that only the top few percentile of places or establishments get the vast majority of attention, and becomes the "must-go meta" for most travellers. Voyago aims to fix this by giving equal exposure to more niche places and asking what *you* like... and what better way to consume large amounts of content than via doomscrolling?! Ultimately, the question comes down to what “motivates one’s happiness”. I want to build a personal agentic AI tour guide who will help you plan your itinerary. The way it does it is to 1. Learn about what is there to do in the city and what about them (places, events, restaurants, etc) 2. Learn and potentially reason about what specific factors “motivate your happiness”, 3. Thus, recommend places for you to go. This is quite an ambitious project that I will continue, and it has a lot of features I have to add to accurately model the constraints someone may have when planning their travels. Currently, the fully processed dataset is limited to restaurants within Vancouver. The demo version contains 47 locations total. This is mainly a proof of concept, but it does work as intended and it demonstrates how, if we're able to process more data of say, attractions, we're able to easily integrate it into this system. But I guess for now it's of some use. I have very strong deciphobia about where to eat and will often spend such a long time walking around, looking at maps, and carefully analysing the menus at the food court, only to resort to McDonalds (the default safe option) in the end

🎫 Golden ticket winner!