Vistara
- 9 Devlogs
- 8 Total hours
A powerful local file discovery engine that helps you quickly find files and information across your computer
A powerful local file discovery engine that helps you quickly find files and information across your computer
Feedback
Hey Paachu,
Awesome project! I'd love to see what you make in the future!
For any other questions, DM @sl4shed or create a ticket in Slack—#ask-the-shipwrights.
Shipwright walkthrough
Feedback
Hey there,
your project seems to integrate Hugging Face. We do not accept Hugging Face, because
- there is no guarantee that they will provide their services free forever.
- it does not teach the user how the project would usually be hosted.
Please change the affected parts of your ship and resubmit!
If you have any other questions, feel free to ask in #ask-the-shipwrights on Slack!
Shipwright walkthrough
Feedback
Hey there, the app just crashes when i launch it. So, i can't approve this ship. Fix this, resubmit, and you should be good!
For any questions, send a message in #ask-the-shipwrights on Slack
Shipwright walkthrough
Feedback
Hey there, this project looks pretty cool. However, in the release notes you mention that Linux/Mac are supported, but when i try to launch the app after running the installer, it crashes instantly. Fix this, resubmit, and you should be good!
For any questions, drop a message in #ask-the-shipwrights or DM @sl4shed on Slack!
Shipwright walkthrough
Feedback
Hey Paachu, thanks for participating in Stardance! However, you seem to have used a lot of AI in your readme. Please rewrite it yourself, as we would like to see how you worked on the project! Also, please make the demo into an executable file, like a .exe or similar, in a GitHub releases. Please fix these things and it should be good to go, thanks!
Shipwright walkthrough
Date: August 18, 2026
Focus: Semantic Search + Hybrid Search
Today I expanded VISTARA from keyword-based search into semantic search, allowing it to understand the meaning behind queries.
all-MiniLM-L6-v2 embedding modelVISTARA can now search using both exact keywords and semantic meaning, making the search much more useful for natural-language queries.
The search engine backend is now essentially complete.
Move towards the remaining polish and then Implement User Interface.
Day 4: Completed ✅
Date: August 17, 2026
Focus: Keyword Search + Chunking
Today I expanded Local Google from basic keyword search into chunk-based search.
chunks database tablechunks_fts FTS5 indexLocal Google can now search through document chunks instead of treating every document as one giant piece of text.
The original Day 4 chunking work was moved into Day 3 because most of it was completed today.
Finish the remaining ranking polish, then move toward semantic search with embeddings.
Day 3: Completed ✅
VISTARA is getting smarter today.
It started as a file scanner that could tell me where my files are. Now it’s learning how to actually read what’s inside them. 🗿
VISTARA can currently process:
.txt.md.pdf.docxIt can scan across the PC while skipping unnecessary system and development folders, keeping the focus on useful documents.
It also uses SHA-256 hashing to detect whether a document is:
The first full scan found 7,462 supported files. 💀
Now VISTARA is going through them one by one, extracting their contents and storing the information in SQLite.
Basically:
"Where tf did I save that file?"
becomes:
"VISTARA, find it." 🗿
And yes… VISTARA is currently eating thousands of files, so my laptop is getting its own workout. 💀🔥
Next up: SQLite FTS5 keyword search.
VISTARA — a local file search engine built to make finding things on your PC less annoying.
First Look Scanning on progress
Project Skeleton Day 1