Khoj

Khoj is an open-source AI personal assistant and second brain.

  • AI
Khoj is an open-source AI personal assistant and second brain. It indexes your notes, documents, bookmarks, and personal files, then lets you search and chat with that content using local (e.g. Ollama, Llama) or cloud-hosted large language models. Built for homelabbers and knowledge workers who want a private, self-hosted assistant that keeps data on their own hardware, Khoj also offers an extensible tool ecosystem for research and content workflows.

Platform availability

Available on 1 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

59/100 Fair

Maintained
67last commit 111 days ago
Popular
9238,183 GitHub stars
Easy to install
251 install platform, install notes
Light to run
304 GB minimum RAM

Availability: platform listings confirmed today

GitHub stars
38,183
Open issues
175
Last commit
2026-08-02
Latest release
2.0.0-beta.28
License
AGPL-3.0
Activity
stale

Checked 2 days ago - source: GitHub (khoj-ai/khoj)

Resources & Compatibility

Minimum requirements: 4 GB RAM, 2 CPU core(s).

Checked 2 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Start Khoj with Docker Compose Create the ~/.khoj folder, download docker-compose.yml there, and run docker-compose up from that folder. This keeps your setup in ~/.khoj and tells you it’s ready when the logs show “🌖 Khoj is ready to engage”. source
  • Tell Emacs which notes to index If you’re using the Emacs client, set khoj-api-key (your sign-in token), khoj-server-url, and khoj-index-directories / khoj-index-files to the folders and files you want searched. Without that, Khoj won’t pick up your important notes. source
  • Set the Mistral key for LiteLLM If you’ll install the LiteLLM proxy, run pip install litellm[proxy], set MISTRAL_API_KEY, then start litellm --model mistral/mistral-tiny --drop_params. Missing the key makes the proxy unable to talk to the Mistral model. source

Fetched 2 days ago - each note links to its source

Alternatives (10)

  • AnythingLLM - AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug…
  • Apertus - As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their spe…
  • Hermes Agent - Hermes Agent is a self-improving AI agent by Nous Research that creates and refines skills from experience, builds a persistent model of yo…
  • Jan.ai - Open-source offline AI chat software supporting local LLMs, cloud model connections, custom assistant creation, OpenAI-compatible API, and…
  • Lumo by Proton - Privacy-first AI assistant with zero-access encryption, no logging or profiling, open-source code, and user-controlled conversations, subje…
  • Manus - Transforms thoughts into actions with personalized travel itineraries, stock analysis, and educational content while autonomously completin…
  • OpenClaw - OpenClaw is an open-source, self-hosted AI assistant gateway that connects large language models (LLMs) to Discord, Telegram, and WhatsApp,…
  • PocketPal - An app that brings language models directly to your phone.
  • Poe - Poe is a web-based AI platform that hosts multiple assistant bots—including Claude and various GPT and image/audio models—to provide conver…
  • Secret Llama - Fully private offline chatbot runs locally in browser, with no server or installation needed.

Checked 2 days ago - source: AlternativeTo

Common questions

How do I start Khoj with Docker Compose and where is its setup stored?

Create a ~/.khoj folder, place docker-compose.yml in that folder, and run docker-compose up from there. Your setup stays in ~/.khoj, and the logs indicate readiness with the ready-to-engage message.

What Emacs configuration do I need for Khoj to find my notes?

Set khoj-api-key to your sign-in token, khoj-server-url to the server address, and khoj-index-directories or khoj-index-files to the folders and files you want searched. Without those settings, Khoj will not pick up those notes.

What must I do to run the LiteLLM proxy for the Mistral model?

Install the proxy with pip install litellm[proxy], set MISTRAL_API_KEY, and start it with litellm --model mistral/mistral-tiny --drop_params. Missing the key prevents the proxy from talking to Mistral.

Which note file types can Khoj index and search?

Khoj understands PDF, plaintext, Markdown, org-mode files, and Notion pages.

Answers sourced from docs.khoj.dev, github.com, github.com, github.com

Community

Collected 2 days ago - public community threads