What is Khoj used for?

Khoj is a self-hostable personal AI app that chats with local or cloud LLMs, answers from the web and your documents, builds custom agents and automates research. It is a good fit for a personal second brain over notes and files, automated recurring research, and private AI assistant using local models.

Yes. Khoj is open source under the AGPL-3.0 licence. Its source code is on GitHub at khoj-ai/khoj and is written mainly in Python.

Yes. Khoj is open source, so the software itself is free to use. A managed cloud version is also available.

Can I self-host Khoj?

Yes. Khoj can be self-hosted on your own server or infrastructure.

What is Khoj an alternative to?

Khoj is an open-source alternative to ChatGPT, Perplexity, Google Gemini and NotebookLM. Other open-source alternatives to ChatGPT include AnythingLLM, Open WebUI and LobeHub.

Is Khoj actively maintained?

Yes. The most recent commit to Khoj was on 2 August 2026, and the latest release is 2.0.0-beta.28, published on 26 March 2026. The project has 38k stars on GitHub.

Khoj: open-source alternative to ChatGPT, Perplexity

About Khoj

Khoj is a personal AI app that you can run on your own machine or scale up to an enterprise cloud deployment. You can chat with local or online models, such as Llama, Qwen, Gemma, Mistral, GPT, Claude, Gemini and DeepSeek, and get answers drawn from the internet and from your own documents, including images, PDFs, Markdown, org-mode files, Word documents and Notion pages.

It can be reached from a browser, Obsidian, Emacs, a desktop app, a phone or WhatsApp. Users create agents with their own knowledge, persona, chat model and tools, set up automations that deliver personal newsletters and smart notifications by email, and use advanced semantic search to find relevant documents. It can also generate images and speak responses aloud. The README highlights benchmark results for retrieval and reasoning and introduces Pipali, a separate open-source AI coworker for your own computer.

Khoj is written in Python and licensed under AGPL-3.0. You can self-host it, with offline models via llama.cpp, or use the hosted app. It suits individuals and teams who want an AI assistant grounded in their notes and files while keeping a choice of model.

Key features

Chat with local or online LLMs
Answers from the web and your documents
Access from Obsidian, Emacs, WhatsApp and browser
Custom agents with their own knowledge and tools
Scheduled automations and newsletters
Semantic search over personal documents

Good fit for

→A personal second brain over notes and files
→Automated recurring research
→Private AI assistant using local models

Built with: Python
Tags: ai-assistant; second-brain; llm; rag; semantic-search; self-hosted; obsidian; agents; python

Khoj: questions and answers

What is Khoj used for?: Khoj is a self-hostable personal AI app that chats with local or cloud LLMs, answers from the web and your documents, builds custom agents and automates research. It is a good fit for a personal second brain over notes and files, automated recurring research, and private AI assistant using local models.
Is Khoj open source?: Yes. Khoj is open source under the AGPL-3.0 licence. Its source code is on GitHub at khoj-ai/khoj and is written mainly in Python.
Is Khoj free?: Yes. Khoj is open source, so the software itself is free to use. A managed cloud version is also available.
Can I self-host Khoj?: Yes. Khoj can be self-hosted on your own server or infrastructure.
What is Khoj an alternative to?: Khoj is an open-source alternative to ChatGPT, Perplexity, Google Gemini and NotebookLM. Other open-source alternatives to ChatGPT include AnythingLLM, Open WebUI and LobeHub.
Is Khoj actively maintained?: Yes. The most recent commit to Khoj was on 2 August 2026, and the latest release is 2.0.0-beta.28, published on 26 March 2026. The project has 38k stars on GitHub.