Khoj
Your AI second brain – open-source personal AI that works on-device or in the cloud.
Smart Download
Visit Project Homepage
No installer available yet — head to the source repository
Open-source personal AI that works locally or in the cloud, supports multiple LLMs and platforms.
Core Features
- Chat with local/cloud LLMs (Llama, GPT, Claude, etc.)
- Get answers from your docs (PDF, Markdown, Notion) and the web
- Access via browser, Obsidian, Emacs, desktop, phone, WhatsApp
- Create custom agents with knowledge base, persona, and tools
- Automate repetitive research, get personalized newsletters and smart notifications
What It Can't Do
- •Self-hosting requires an LLM API key; cloud service has free tier but may charge for heavy usage; basic technical knowledge needed for self-hosting.
Use Cases
- Quickly find information across personal notes and documents
- Build a custom Q&A assistant for your knowledge base
- Automate research report generation and email summaries
Detailed Introduction
Khoj is a personal AI app that extends your capabilities. It seamlessly scales from on-device to cloud. Chat with any local or online LLM (Llama, GPT, Claude, etc.), get answers from your docs and the web, and access it from browser, Obsidian, Emacs, desktop, phone, or WhatsApp. Create custom agents, automate research, receive smart notifications, and generate images. Fully open-source and self-hostable, Khoj keeps your data private while offering enterprise-grade features.
Troubleshooting & FAQ (2)
TroubleshootingHow to make Khoj work with a self-hosted Firecrawl instance?
Set the FIRECRAWL_API_URL environment variable to your self-hosted Firecrawl URL. For Docker, use the pre-release image (khoj:pre) until Khoj 2.0 stable is released. Example: export FIRECRAWL_API_URL=http://localhost:3002, then restart Khoj. This fix is included in PR #1276 and Khoj 2.0-beta.
TroubleshootingWhy does 'pip install khoj' fail with a dependency conflict on Python 3.13?
Khoj currently does not support Python 3.13. The workaround is to downgrade to Python 3.12. Create a virtual environment with Python 3.12, then run 'pip install khoj'. This dependency constraint will be documented in future releases.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Use online: go to https://app.khoj.dev – no setup needed
Self-host: pip install khoj or run via Docker
Configure LLM API key and document folders, then start chatting
- Use online: go to https://app.khoj.dev – no setup needed
- Self-host: pip install khoj or run via Docker
- Configure LLM API key and document folders, then start chatting
Checksum not available
This project has not published a SHA-256 checksum on its GitHub Release page
SHA256 Checksum
No checksum available
Download directly from GitHub Releases and verify file integrity yourself
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
If installed via pip: pip uninstall khoj; if using Docker: remove container and image.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
2 FAQs
Similar Projects
airi
A self-hosted, open-source AI companion inspired by Neuro-sama, capable of realtime voice chat and playing games like Minecraft and Factorio. Fully cross-platform (Web/Mac/Windows).
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).