Khoj
Open-source AI second brain with local SLMs, documents, and web search
About Khoj
Khoj is an open-source AI desktop assistant and personal second brain that allows users to search, chat, and synthesize insights across their personal notes, documents, and code repositories. Operating seamlessly with local SLMs (via Ollama) or hosted frontier models, Khoj prioritizes user privacy and offline autonomy. Whether indexing Obsidian markdown vaults, PDF research papers, Emacs org-mode files, or browser bookmarks, Khoj acts as a unified knowledge retrieval agent that answers complex multi-hop questions directly from your private workspace.
Khoj supports scheduled automated research agents that browse the web, compile daily intelligence briefings, and synthesize relevant industry updates directly to your inbox or WhatsApp. The architecture combines dense embeddings with hybrid local vector indexes, ensuring sub-second response times on standard consumer laptops. Developers can run Khoj as a native desktop client, Emacs package, Obsidian plugin, or private self-hosted Docker server with complete offline privacy.
Install Khoj via Docker, the native desktop application, or the cloud hosted dashboard.
Connect your local knowledge sources (Obsidian vault, PDF library, GitHub repos, or Notion workspace).
Select your preferred AI model: local Ollama models (Llama 3, Mistral) for privacy or cloud models for complex reasoning.
Ask questions in natural language to search across all your documents simultaneously.
Configure autonomous research agents to monitor web topics and generate recurring synthesized summaries.
Capabilities & Features
Common Use Cases
personal-knowledge-management
offline-ai-chat
document-search
automated-research
obsidian-ai
Frequently Asked Questions
Can Khoj run completely offline?
Yes, Khoj can run 100% offline on your local computer when paired with Ollama or local small language models without transmitting any data over the internet.
Does Khoj integrate with Obsidian?
Yes, Khoj provides an official Obsidian community plugin that allows you to chat with your markdown vault directly inside Obsidian.
Is Khoj free?
Yes, the self-hosted open-source version of Khoj is completely free with no usage limits. A hosted cloud subscription is available for $8/month.
Free Plan
100% free and open-source self-hosted version with unlimited local document indexing
Paid Plan
Cloud hosted plan at $8/mo with hosted GPT-4o, Claude 3.5, and automated web research agents
Pros & Cons
100% open source with complete local offline privacy and zero telemetry
Native plugins for Obsidian, Emacs, and desktop operating systems
Supports local models via Ollama as well as hosted frontier LLMs
Autonomous recurring web research agents deliver briefings to email and chat
Blazing fast hybrid semantic retrieval across private document collections
Self-hosting local LLMs requires modern computer hardware with sufficient RAM and VRAM
Cloud plan required for users who do not want to manage local Docker containers
Alternatives
View allMem0
The universal persistent memory layer for AI agents & LLM apps
Mem0 (formerly Embedchain) is a universal, persistent memory architecture designed to solve the critical context amnesia problem in modern AI applications. While foundational LLMs forget user preferences and past interactions the moment a session ends, Mem0 maintains a continuous, self-improving memory graph across user sessions, agents, and applications. With Mem0, developers can build personalized AI assistants, customer support agents, and autonomous workflow bots that remember user preferences, past project decisions, and communication styles over months and years. Mem0 operates as both an open-source self-hostable Python/TypeScript library and a managed cloud platform, providing sub-100ms vector search, episodic memory extraction, and automated memory consolidation without manual prompt engineering.
NotebookLM
AI-powered research assistant
NotebookLM is Google's AI-powered research and note-taking tool that lets you upload your own documents and interact with them using natural language. It helps summarize sources, generate insights, and answer questions based on your uploaded content.
Qdrant
High-performance vector database and similarity search engine for AI
Qdrant is an open-source, high-performance vector database and similarity search engine engineered in Rust for production AI systems, semantic search engines, and Retrieval-Augmented Generation (RAG) pipelines. It provides lightning-fast nearest-neighbor search with rich payload filtering and custom distance metrics. Unlike traditional databases adapted for vectors, Qdrant was designed from day one to handle high-dimensional neural embeddings at scale. Its Rust engine provides memory-efficient vector quantization (scalar, product, and binary), allowing engineering teams to search billions of vectors on cost-effective cloud hardware.
Julius AI
Your personal data scientist
An AI assistant that can analyze spreadsheets, perform statistical tests, and generate beautiful data visualizations from natural language.
World Labs
Building AI models to perceive and interact with 3D worlds.
World Labs develops foundational AI models for spatial intelligence and 3D understanding. Their technology enables machines to perceive and interact with the physical world in three dimensions. The company aims to bridge the gap between digital and physical environments.
SciSpace
Your AI research workspace
An all-in-one research platform with a powerful 'Copilot' for reading and understanding complex papers.
Compare Khoj with Alternatives
Side-by-side feature, pricing, and pros & cons breakdowns