Artificial Intelligence

Khoj

Khoj — self-hosted personal AI assistant: semantic search on notes and docs, autonomous agents, Obsidian and browser extension support.

Official documentation

About Khoj

Khoj is an open-source AI assistant (AGPL-3.0) you self-host on your own VPS. It automatically indexes your Obsidian notes, PDF documents and text files, letting you ask natural language questions and trigger autonomous agents that can search the web. Access it from the web interface, Chrome and Firefox browser extensions, or the Obsidian plugin.

What gets installed

Ready when the VPS starts

Compatible OS
Choice of Linux distributions
Application
Khoj
Tech stack
Docker ComposePythonPostgreSQL 15 + pgvectorFastAPI
Minimum RAM
4 GB minimum (8 GB recommended)
Minimum CPU
2 vCPUs minimum
Default port
42110
Access
root over SSH

Key features

  • Semantic search on your notes, PDFs and documents — no cloud involved
  • Autonomous agents that browse the web and aggregate sources
  • Native Obsidian integration, Chrome and Firefox extensions, web interface
  • Works with local LLMs via Ollama or OpenAI / Anthropic APIs
  • PostgreSQL + pgvector backend: fast indexing and vector search
  • Multimodal: ask questions about images embedded in your notes

When to use this solution?

Technical knowledge base

Query your Obsidian vault of technical documentation without leaving your IDE. Khoj finds architecture decisions, useful commands and meeting notes by meaning, not by keyword.

Legal or HR document research

Load your contracts, internal procedures and regulatory texts. Ask precise questions about your data without exposing any document to a third-party service.

News monitoring and synthesis

Khoj agents can query the web, aggregate multiple sources and deliver a structured summary directly from the interface or browser extension.

Guide

Deploy Khoj on your VPS

  1. Order a ServOrbit VPS

    Plan for at least 4 GB of RAM and 2 vCPUs. Khoj loads embedding models at startup: an undersized server causes significant indexing delays.

  2. Point your domain to the VPS

    Khoj requires a FQDN for its authentication URLs and task callbacks. Add an A record at your registrar before deploying.

  3. Deploy Khoj from the ServOrbit catalog

    Choose the Khoj app in the AI category. ServOrbit generates a random admin password, installs the Docker Compose stack (PostgreSQL + pgvector + Khoj server) and configures nginx with your domain.

  4. Log in and configure a LLM

    Access the web interface with email [email protected] and the password shown in your client area. Go to Settings → LLM to connect Ollama (local) or your OpenAI key.

  5. Connect the Obsidian plugin

    Install the official Khoj plugin from the Obsidian library (Settings → Community plugins → Khoj), enter your instance URL and API key. Vault indexing starts immediately.

Frequently asked questions

Questions about Khoj

← Back to Artificial IntelligenceAll applications
No. Khoj runs on CPU only: it delegates LLM inference to your configured LLM (local Ollama, OpenAI API, etc.) and does not embed any generation model internally. The only local load is document embedding, which remains modest.

Embed the deploy button

Maintaining a project that uses Khoj? This button lets your readers deploy it on a VPS in one click, without reading Docker documentation.

Deploy Khoj on ServOrbit
Markdown
[![Deploy Khoj on ServOrbit](https://servorbit.com/brand/deploy/button.svg)](https://servorbit.com/vps-cloud?template=khoj&utm_source=deploy-badge&utm_medium=referral&utm_campaign=khoj)
HTML
<a href="https://servorbit.com/vps-cloud?template=khoj&utm_source=deploy-badge&utm_medium=referral&utm_campaign=khoj"><img src="https://servorbit.com/brand/deploy/button.svg" alt="Deploy Khoj on ServOrbit" height="40"></a>

The button points to a VPS order with the template preselected. The image is served from servorbit.com — nothing to host on your side.

Complementary solutions

Artificial Intelligence

AnythingLLM

Open-source AI workspace with built-in RAG, AI agents, and multi-model chat. Connect your own documents, use any LLM — hosted privately on your VPS.

Artificial Intelligence

Open WebUI

Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.

Artificial Intelligence

PrivateGPT

Local document RAG assistant: ask questions of your PDFs, contracts and team notes — LLM and embeddings run on your VPS, zero data leaving the server.

Need help?

Browse our help center and FAQ, or reach our team — callback, WhatsApp or email.

Message us on WhatsAppopens in a new tab
or write to us