Khoj
Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI.
Maintained, but at a slower pace than the leaders in its category.
Commit activity more than 34% of tracked projects; popularity more than 94%. How this is calculated.
Commits, last 11 months
| Stars | 38k |
|---|---|
| Latest release | 2.0.0-beta.28 · 26 Mar 2026 |
| Repo updated | 2 Aug 2026 |
| Licence | AGPL-3.0 |
| Built with | Python, Docker |
Is Khoj actively maintained?
Khoj is under active development: 120 commits landed over the last 11 months, averaging roughly 4 commits a month in the most recent quarter.
Activity is cooling: commits are down 52% against the previous quarter. One slow quarter is normal; two in a row is a signal.
The most recent tagged release, 2.0.0-beta.28, is about 6 months old.
Khoj ranks #14 of 14 tracked generative artificial intelligence (genai) projects. Several better-maintained options exist in the same category — they are listed below.
What Khoj actually does
Khoj is a self-hosted AI assistant designed to retrieve answers from the internet or local documents. It allows you to construct custom agents, schedule automations, and conduct research using either online or local language models.
Best fit: It suits technical users who want to query their personal documentation and automate workflows using self-hosted or cloud-based language models.
Worth knowing: The AGPL-3.0 licence requires you to release the complete source code of your modified version if you offer it as a network service, which may affect commercial usage.
Deployment notes
As a Python application packaged with Docker, it typically requires persistent volumes for data storage and a reverse proxy to handle TLS termination.
Alternatives to Khoj
Projects in the same categories, ordered by health score.
Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking.
User-friendly AI Interface, supports Ollama, OpenAI API.
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).
Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, and plugin support.
Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.