HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
eagledot
hachi
Python2023–2025
eagledot / hachi

hachi

An end to end semantic and meta-data search engine for personal data.

5Distinct people
14Mentions
0Explicit recommenders
325GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

An end to end semantic and meta-data search engine for personal data.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 4:59:52 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by year14 dated mentions

Observed mentions: 2023-03-27 11:13:04 UTC to 2025-12-06 11:24:07 UTC.

024682023-01-01 00:00:00 UTC to 2024-01-01 00:00:00 UTC (exclusive): 8 mentions; 4 submissions, 4 comments20232024-01-01 00:00:00 UTC to 2025-01-01 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments20242025-01-01 00:00:00 UTC to 2026-01-01 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2025

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
20232023-01-01 00:00:00 UTC2024-01-01 00:00:00 UTC844
20242024-01-01 00:00:00 UTC2025-01-01 00:00:00 UTC404
20252025-01-01 00:00:00 UTC2026-01-01 00:00:00 UTC202

What Hacker News says

8 sources
I think, it is really underrated how much faster numpy approach is for low-key workloads like personal images and videos where you would generally have a few K embeddings and it is also possible to hide some latency by sharding and stream results as soon as a shard is done. We work on a similar project[0] to make it easy to index personal images and videos. Before using numpy, we also looked at libraries like Annoy to index the embeddings, but being approximate sometimes such libraries would leave out most-similiar image/frame. For personal data, we found it is better to depend on exact-search rather than an approximate one even if it comes with a speed tradeoff. [0]: https://github.com/ramanlabs-in/hachi
In Do you need a vector database?
warangal·Mar 27, 2023Submission

Show HN: Self-hosted natural language search for videos and images

Hi, I am Anubhav from ramanlabs. We have been working on a self hosted solution to enable natural language search for videos and images. Idea is to allow users to Index all locally available images and videos just once, and then later query them using natural language. It doesn't depend on any deep-learning framework and should make installation easier and faster. All Indices are stored locally without no dependence on outside network. Semantic search is powered by CLIP architecture. We already have some features on the roadmap and are interested in hearing your feedback/thoughts. Github: <https://github.com/ramanlabs-in/hachi> Demo: <https://demo.ramanlabs.in>
4 points · Open discussion

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.