Khoj

Khoj indexes local documents, notes, and files into a searchable knowledge base using semantic embeddings, enabling retrieval of contextually relevant information across heterogeneous sources (markdown, PDFs, text files, etc.). The system maintains a local or cloud-hosted vector index that maps document chunks to embeddings, allowing natural language queries to surface relevant context without keyword matching. This indexed knowledge is then injected into the agent's context window for grounded responses.

Khoj enables the agent to search the web in real-time and retrieve current information from online sources, augmenting local knowledge with live data. The agent can invoke web search as a tool during reasoning, fetching and parsing search results to answer questions about current events, recent publications, or information not present in local documents. Search results are ranked and summarized before injection into the LLM context.

Khoj can extract structured information (entities, relationships, tables, metadata) from documents and web content using LLM-based extraction with optional schema guidance. Extracted data can be formatted as JSON, CSV, or other structured formats, enabling integration with downstream systems. The extraction process can be applied to individual documents or batched across large collections.

Allows users to configure LLM parameters (temperature, top-p, max tokens, etc.) and embedding model selection to tune assistant behavior and performance. Provides configuration interfaces for adjusting generation quality, response length, and semantic search sensitivity without code changes.

Khoj abstracts away LLM provider differences through a unified interface, allowing users to configure any supported model (OpenAI, Anthropic, Ollama, local models, etc.) as the agent backbone. The system handles prompt formatting, token counting, and API calls transparently, enabling users to swap models without changing agent logic or tool definitions. This abstraction supports both cloud-hosted and self-hosted model deployment.

Khoj maintains conversation history across multiple turns, managing context windows and token budgets to keep relevant prior exchanges accessible to the agent while respecting model token limits. The system implements context compression or summarization strategies to preserve conversation coherence without exceeding token budgets. Memory can be persisted across sessions for long-term conversation continuity.

Khoj can generate written content (emails, blog posts, summaries, etc.) using the configured LLM, optionally grounded in indexed documents or web search results. The system supports templates and structured prompts to guide content generation toward specific formats or styles. Generated content can be edited, refined, and exported in multiple formats.

Khoj (via the Pipali product) can schedule and execute automated tasks on a local machine, such as periodic research, document processing, or data collection. Tasks run 'safely on your computer' with defined execution schedules and can integrate with local tools and scripts. The system manages task state, logging, and error handling for autonomous execution.

Khoj provides a conversational chat interface where users ask questions in natural language and receive contextually grounded answers. The agent processes queries by combining indexed document search, optional web search, and LLM reasoning to synthesize responses. Responses include citations to source documents or web results, enabling users to verify information and explore sources.

Khoj can be deployed as a self-hosted application (on personal machines, servers, or containers) or accessed as a cloud service, giving users flexibility in infrastructure choice. Self-hosted deployment provides full data control and privacy, while cloud deployment offers convenience and reduced operational overhead. The same agent logic works across both deployment modes.

Khoj integrates with popular note-taking systems (Obsidian, Logseq, Roam Research, etc.) and productivity tools, automatically indexing notes and enabling the agent to access and reason over personal knowledge graphs. Integration typically works through file system access or API connections, keeping the knowledge base synchronized with the user's existing tools.

Khoj can autonomously conduct research tasks by combining web search, document retrieval, and LLM reasoning to gather and synthesize information on specified topics. The agent can be configured to research topics, compare sources, identify gaps, and produce structured research summaries. Research tasks can be scheduled to run periodically, building up research dossiers over time.