Logo
Deploy Now

SaaS Alternative

ChatGPT Plus Notion AI Mem Rewind

Categories

Productivity AI Knowledge Management Notes RAG Personal Assistant Semantic Search Second Brain

Stars

35990

Forks

2322

Watchers

170

Developer links

Last Updated: 07-25-2026 06:13 PM (UTC)

Khoj

A self-hosted "second brain": Khoj indexes your own files and answers questions from them, parsing Markdown (whole Obsidian vaults included), org-mode, PDF, Word, plain text, Notion pages, GitHub repositories, and images described by a vision model, then embedding everything with sentence-transformers into a vector index for semantic search and RAG with cited sources. Any LLM backend works: local models like Llama, Qwen, or Mistral via Ollama, or cloud models like GPT, Claude, and Gemini. You can build custom agents, each with its own persona, scoped knowledge base, chat model, and tools such as web search and code execution. Scheduled automations run recurring research and deliver newsletters or notifications to your inbox, and research mode performs multi-hop web searches with inline citations. Access it from a browser, the Obsidian plugin, Emacs, desktop, or WhatsApp - all clients connect to the same self-hosted instance, making Khoj one of the few AI assistants Emacs users can point at decades of org files. Semantic search means recall works without exact keywords: "that paper about forecasting with transformers" surfaces the right PDF even when you cannot remember its title. Switching LLM backends never requires re-indexing your documents, and with a local model via Ollama, even inference stays on hardware you control - journals, research, and private notes are never sent anywhere. Python/FastAPI stack, AGPL-licensed, with PostgreSQL storage.

Khoj

Benefits

  • Your Notes Never Leave Your Server
  • Journals, research, and private documents are indexed and queried on your own instance. With a local LLM via Ollama, even inference stays on hardware you control.
  • Recall Without Exact Keywords
  • Semantic search finds notes by meaning, so 'that paper about forecasting with transformers' surfaces the right PDF even when you cannot remember its title or wording.
  • Native to Plain-Text Workflows
  • First-class support for Markdown, Obsidian vaults, and org-mode, one of the few AI assistants Emacs users can point at decades of org files, with clients embedded in both editors.
  • Research on a Schedule
  • Automations run recurring queries and deliver digests to your inbox, turning repetitive monitoring tasks into standing orders your assistant handles.

Features

  • Broad Document Indexing
  • PDF, Markdown, org-mode, Word, plain text, Notion via API, GitHub repositories, and images interpreted by vision models, all embedded into a semantic vector index.
  • RAG Chat with Citations
  • Questions retrieve the most relevant chunks from your corpus and answers cite the source documents, so responses are verifiable against your own files.
  • Any LLM Backend
  • Configure local models through Ollama or cloud providers like OpenAI, Anthropic, and Google, and switch backends without re-indexing your documents.
  • Custom Agents
  • Create assistants with a specific persona, a scoped subset of your knowledge base, a chosen chat model, and tool access including web search and code execution.
  • Research Mode and Automations
  • Multi-hop web research with inline citations, plus scheduled tasks that deliver personal newsletters and smart notifications by email.
  • Multiple Clients
  • Web browser, Obsidian plugin, Emacs package, desktop app, and WhatsApp all connect to the same self-hosted instance.