khoj and Lore
These two tools are competitors, as both aim to be a self-hostable, local LLM agent that processes user documents and web content into a vectorized database for querying and personalized knowledge management, differing primarily in feature breadth and user base.
About khoj
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.
Supports semantic search and RAG across multiple document formats (PDF, Markdown, Notion, Word, org-mode), with configurable agents that combine custom knowledge bases, personas, and tools. Uses a modular architecture enabling deployment across browsers, Obsidian, Emacs, desktop, mobile, and WhatsApp via unified APIs. Integrates with both local LLMs (Llama, Qwen, Gemma, Mistral) and cloud providers (OpenAI, Claude, Gemini), plus web search and automation scheduling capabilities.
About Lore
ErezShahaf/Lore
Summon it with a keystroke, throw in anything you want to remember or ask your own memory. A local LLM agent that restructures your knowledge into a vectorized DB. fully private, zero cloud. Built for developers.
Integrates Ollama for local LLM inference and LanceDB for vector storage, enabling RAG-powered retrieval with automatic input classification (thought/question/command/instruction). Built as an Electron desktop app with global hotkey activation, it also includes todo management and supports custom system instructions to personalize response formatting and behavior.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work