Khoj

Khoj is a self-hosted artificial intelligence platform designed for personal knowledge management and semantic information retrieval. It functions as a private assistant that indexes your local documents, notes, and external workspaces, allowing you to interact with your data through natural language queries and conversational chat. By maintaining a local-first architecture, the system ensures that your information remains under your control while providing context-aware responses grounded in your personal knowledge base.

The platform distinguishes itself through a modular, cross-platform integration layer that embeds intelligent search and chat capabilities directly into your existing workflows. Whether you are working within text editors, web browsers, or mobile messaging applications, Khoj provides a unified interface to your data. It supports advanced retrieval strategies, such as dual-model architectures for semantic mapping and real-time internet grounding, which allow the assistant to synthesize private notes with external information while providing clear source citations.

Beyond its core retrieval capabilities, the system offers a comprehensive suite of tools for data orchestration and research automation. It includes a pluggable ingestion pipeline for diverse file formats, automated query scheduling, and the ability to execute code or generate visual content directly within the chat interface. Users can configure custom agents, manage model routing, and secure their deployments with multi-user authentication, making it suitable for both individual use and enterprise-grade environments.

Features

Personal AI Assistants - Enables the creation of a personal AI assistant that indexes local documents and web content to automate research.
Semantic Search Engines - Performs context-aware searches across diverse file formats using vector embeddings.
Personal Knowledge Management Systems - Organizes and retrieves information from private notes and documents using natural language search and AI-assisted discovery.
Semantic Search Engines - A retrieval tool that uses vector embeddings to perform conceptual searches across diverse personal data sources and local file systems.
Vector Indexing Engines - Converts unstructured text into high-dimensional numerical embeddings to enable fast similarity searches.
Self-Hosted AI Infrastructure - Deploys and manages private artificial intelligence services on local hardware to maintain full control over data and processing.
Private Data Privacy Tools - Enables conversational interaction with personal data while ensuring privacy through local-first processing and secure remote access.
Retrieval Architectures - Implements dual-model architectures to map queries and documents into a shared vector space for context-aware retrieval.
Retrieval-Augmented Generation - Grounds responses in real-time internet data by automatically performing web searches when fresh information is required.
Self-Hosted AI Models - Khoj allows deployment of the AI assistant on private infrastructure to maintain control over data, configuration, and model selection.
Enterprise Deployment Solutions - Khoj provides enterprise-grade deployment options, offering secure access and custom integration capabilities for teams and businesses.
Self-Hosted AI Platforms - Manages private data indexing and model orchestration while maintaining full control over user information.
Agent Configurations - Allows users to define custom system prompts to create specialized agents that perform specific roles.
Inference Orchestrators - Manages model execution across local hardware and remote gateways to balance privacy and performance.
Local Model Runners - Connects to a local model runner to execute large language models directly on self-hosted hardware.
Agentic Applications - Self-hosted knowledge base for documents and web content.
AI Search Engines - Personal AI assistant for searching and interacting with documents.
Autonomous Agents - Personal AI assistant for knowledge management and search.
Note Taking Search - Searches through personal notes using natural language queries powered by machine learning models.
Editor AI Assistants - Enables iterative AI-assisted conversations for content generation and discovery within the text editor.
Note-Taking App AI Assistants - Facilitates AI-assisted information retrieval and content generation within the note-taking application.
Self-Hosted Applications - Khoj supports deployment on private hardware to maintain full control over data processing, storage, and personal information indexing.
AI Code Interpreters - Generates and runs Python code to perform data analysis, create visualizations, or handle complex quantitative tasks.
Chat Interaction Controls - Supports commands within chat queries to specify information sources, generate images, or run code snippets for precise responses.
Data Indexing Tools - Processes diverse data sources including documents, code repositories, and web pages using modular natural language models.
Data Ingestion Pipelines - Uses pluggable connectors to normalize and index diverse file formats into a unified searchable knowledge base.
Data Ingestion Tools - Enables users to upload personal data files to the platform for searching, chatting, and interacting with their own documents.
Editor Search Integrations - Performs natural language searches across private notes or the public internet directly from the editor.
Local File Syncing - Connects local folders to the application to provide context for search results and conversational responses.
Authentication Strategies - Secures multi-user access for self-hosted instances using authentication methods like Magic Links or OAuth.
Web Search Interfaces - Performs fast, incremental, and local-first searches across personal data for a responsive search experience.
Workspace Integrations - Connects Notion workspaces by configuring API keys and integration settings to enable searching and chatting with external data.
Data Synchronization Tools - Combines personal notes, documents, and folders from various sources for use in unified chat interactions.
Incremental Indexing Mechanisms - Monitors file systems and data sources to incrementally update the search index upon content changes.
Query Filtering Systems - Narrows down search results and chat responses by applying structured query syntax to target specific entries.
Cross-Platform Tooling - Connects AI-powered search and chat capabilities across multiple editors, browsers, and mobile devices.
Editor Integrations - Khoj allows users to interact with their personal knowledge base and second brain directly from within the text editor environment.
Editor Plugins - Embeds intelligent search and chat capabilities directly into existing text editors and messaging applications.
Note-Taking App Knowledge Interfaces - Allows interaction with personal knowledge bases and second brains directly from within the note-taking application.
Desktop Chat Interfaces - Provides a dedicated desktop application for natural language conversations to retrieve information from personal collections.
Web Chat Interfaces - Offers a web-based AI assistant for retrieving information from private notes or the internet.
Web Interfaces - Provides a standard web browser interface to interact with personal knowledge bases and retrieve information from any device.

getumbrel/llama-gpt

10,991View on GitHub

Llama-GPT is a self-hosted generative AI model runner that provides a private web interface for interacting with large language models. By executing these models directly on local hardware, it ensures that all intelligent assistance remains offline and independent of external cloud service providers. The project functions as a private assistant that maintains complete data ownership by storing all application state and model interactions on local storage volumes. It is designed to operate within a broader self-hosted computing environment, allowing users to maintain control over their persona

go-skynet/LocalAI

47,157View on GitHub

LocalAI is a local generative AI platform and inference engine designed to host large language, vision, and audio models on private hardware. It functions as an API compatible gateway that mimics proprietary service endpoints, allowing existing third-party software to integrate with a self-hosted backend. The platform distinguishes itself as a distributed AI model orchestrator, capable of scaling inference across machine clusters using VRAM-aware routing and hardware coordination. It provides a unified interface for diverse open-source backends and supports self-hosted RAG infrastructure thro

beclab/Olares

4,086View on GitHub

Olares is a comprehensive suite of self-hosted identity, storage, AI, and orchestration services designed for private infrastructure management. It functions as a Kubernetes home server orchestrator, enabling the deployment of containerized applications, AI models, and GPU resources on local hardware to replace third-party cloud services. The platform distinguishes itself through a combination of self-hosted AI infrastructure for running large language models and image generators, alongside a decentralized identity manager that uses cryptographic keys and OIDC for trustless authentication. It

nesquena/hermes-webui

14,912View on GitHub

Hermes-webui is a self-hosted AI orchestrator and web interface for managing autonomous agents. It serves as a multi-provider gateway that connects cloud and local large language models, providing a central hub to execute scheduled background jobs, run shell commands, and manage agent memory on private hardware. The system distinguishes itself through a persistent memory manager that utilizes knowledge graphs and markdown files for long-term context across sessions. It features a model context protocol host for extending agent capabilities with standardized tools and supports the orchestratio

khoj-aikhoj

Features