# khoj-ai/khoj

Your AI second brain. Self-hostable. 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 (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

Repository: https://github.com/khoj-ai/khoj
Canonical: https://ross.abutalabs.com/products/khoj
Homepage: https://khoj.dev
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: semantic-search, emacs, obsidian-md, chat, chatgpt, ai, llm, productivity, agent, self-hosted, rag, whatsapp-ai, offline-llm, llamacpp, obsidian, llama3, image-generation, stt, assistant, research
Last push: 2026-08-02T01:55:40+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 95, release rhythm 64, longevity 100
- inputs: {"age_days": 1844, "days_push": 32, "days_rel": 160, "gap_med": 2, "n_releases_24m": 76}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 36730, forks 2409 (observed 2026-08-28T04:12:01.236223+00:00)

## What it is
Khoj is a self-hostable personal AI assistant ('second brain') that answers questions from your own documents and the web using local or online LLMs. It supports custom agents, scheduled automations, semantic search, image generation, and voice, accessible via browser, Obsidian, Emacs, desktop, phone, or WhatsApp.

## Use cases
- chat with my own documents using a local llm
- self-hosted chatgpt alternative over my notes
- semantic search across obsidian and markdown notes
- build custom ai agents with my own knowledge
- automate research and get newsletters from an ai
- query pdfs and notion docs with an ai assistant
- run an offline ai assistant on my computer

## When to choose
- you want a private, self-hosted AI assistant over your personal docs
- you use Obsidian, Emacs, or WhatsApp and want AI integrated there
- you need RAG with support for local models like llama or mistral
- you want agents, automations, and deep research in one app

## When to avoid
- you only need a simple hosted chatbot without self-hosting overhead
- you need a lightweight library to embed RAG in your own app rather than a full application
- you require enterprise SaaS support and managed infrastructure

## Facets
- artifact type: application
- maturity: active
- function: rag, search-engine, chatbot, agent-framework, llm-inference, speech-recognition, image-processing, workflow-automation, web-scraping
- domain: artificial-intelligence, large-language-models, developer-tools, self-hosted
- platform: self-hosted, python, cross-platform, browser
- tags: second-brain, semantic-search, obsidian, emacs, whatsapp, offline-llm, personal-assistant, deep-research, retrieval-augmented-generation, ai-agents, natural-language-processing, web-server, docker, desktop, mobile

## Member repositories
- khoj-ai/khoj (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.236223+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:25:55.190987+00:00, confidence not recorded.
  - readme: https://github.com/khoj-ai/khoj (fetched 2026-08-28T04:12:01.236223+00:00, sha 302132041bf3)
  - homepage: https://khoj.dev (fetched 2026-08-29T07:47:26.940538+00:00, sha 7e371e101622)
- Data as of 2026-08-30T08:39:29.467469+00:00.