Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Search the web and your self-hosted apps using local AI agents.
| Date | Stars |
|---|---|
| 2026-07-31 | 572 |
| 2026-08-06 | 572 |
| 2026-08-14 | 573 |
| 2026-08-19 | 574 |
| 2026-08-21 | 574 |
| 2026-09-04 | 575 |
| 2026-09-12 | 576 |
| 2026-09-13 | 575 |
| 2026-09-20 | 575 |
Today
— stars today
This week
— stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.00%/day
<br/>
<div align="center">
<a href="assets/icon-frameless.png">
<img src="assets/icon-frameless.png" alt="Logo" width="100" height="100">
</a>
<h3 align="center">Perplexideez</h3>
<p align="center">
Self-hosted AI-powered search.
<br/>
<br/>
<a href="https://github.com/brunostjohn/perplexideez/issues/new?labels=bug&template=bug_report.md">Report Bug</a> ·
<a href="https://github.com/brunostjohn/perplexideez/issues/new?labels=enhancement&template=feature_request.md">Request Feature</a>
</p>
</div>
<h3 id="aboutTheProject">About The Project</h3>
There are many self-hosted Perplexity clones out there. I chose to make my own as I was dissatisfied with their non-existent integration with other self-hosted services and lack of multi-user support. Perplexideez is backed by a Postgres database & either Ollama or OpenAI compatible endpoints. It searches the web using a SearXNG instance.
### Table of Contents
1. [About The Project](#aboutTheProject)
2. [Features](#features)
1. [Search the web](#features-searchTheWeb)
2. [Know where conclusions come from](#features-knowWhere)
1. [Learn even more](#features-knowWhere-learnMore)
3. [Keep track of your most interesting searches](#features-keepTrack)
4. [Customise your experience](#features-customise)
5. [Multi-user support & SSO](#features-multiUser)
6. [Sharing searches](#features-sharing)
1. [Simple UI](#features-sharing-simple)
2. [Access control](#features-sharing-accessControl)
3. [Good looking embeds](#features-sharing-embeds)
7. [Deployment](#features-deployment)
1. [Security](#features-deployment-security)
2. [Statelessness](#features-deployment-statelessness)
3. [Deploying](#deploying)
1. [Container images](#deploying-images)
2. [Docker](#deploying-docker)
3. [Kubernetes](#deploying-kube)
4. [Bare metal](#deploying-metal)
5. [General notes about dependencies](#deploying-notes)
1. [SearXNG](#deploying-notes-searxng)
6. [Environment variables](#deploying-env)
1. [Data storage](#deploying-env-data)
2. [App setup](#deploying-env-app)
3. [SSO](#deploying-env-sso)
1. [Notes](#deploying-env-sso-notes)
4. [SearXNG](#deploying-env-searxng)
5. [AI setup](#deploying-env-ai)
1. [OpenAI](#deploying-env-ai-openai)
2. [Ollama](#deploying-env-ai-ollama)
4. [Built with](#builtWith)
5. [Developing locally](#developingLocally)
1. [Prerequisites](#developingLocally-pre)
2. [Installation](#developingLocally-install)
6. [Roadmap](#roadmap)
7. [Contributing](#contributing)
8. [License](#license)
9. [Contact](#contact)
10. [Acknowledgments](#acknowledgments)
<h3 id="features">Features</h3>
<h4 id="features-searchTheWeb"> Search the web </h4>
Let AI do the hard work of sifting through search results for you.
<h4 id="features-knowWhere"> Know where conclusions come from </h4>
Don't worry about hallucinations ruining your research. Just hover over the source annotation your LLM inserted and see the source it used. Click on it, and view the source directly.
<h5 id="features-knowWhere-learnMore"> Learn even more </h5>
Your LLM will generate great follow-up questions for you. This way, you can ask about what interested you in the response without typing a single second.
<h4 id="features-keepTrack"> Keep track of your most interesting searches </h4>
Stash your favourite searches as favourites. This way, you'll never lose them.
<h4 id="features-customise"> Customise your experience </h4>
Perplexideez lets you use different models for different tasks, as appropriate. The robust environment variables and UI configuration allow you to make sure your self hosted resources are not overused.
<h4 id="features-multiUser"> Multi-user support & Excerpt of 14,827 characters
Read on GitHub
88
Ikko Eltociear Ashimine · Japan
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:af9c9daccb471065, desc:ai agents