kotaemon vs local-deep-research

Self-hosted AI tools for documents and research compared

kotaemon provides a customizable document question-and-answer app built around RAG, while local-deep-research searches web, academic, and configured private sources to produce cited reports. Both support local or hosted models, but kotaemon centers on querying documents and tuning a RAG pipeline, whereas local-deep-research centers on gathering and synthesizing research across sources.

kotaemonlocal-deep-research
LanguagePythonPython
LicenseApache-2.0MIT
Stars25.8k9.2k
Forks2.2k839
Last analyzedOct 24, 2026Oct 11, 2026

Key differences

  • kotaemon focuses on document chat, retrieval, and answer inspection; local-deep-research combines live web and academic search with private-document research and report generation.
  • kotaemon highlights hybrid full-text and vector retrieval, reranking, PDF citations, and multimodal document QA; local-deep-research highlights agentic source selection, structured reports, and Markdown or PDF export.
  • kotaemon provides a Gradio-based web interface and customizable RAG pipelines; local-deep-research also provides Python and HTTP APIs and an MCP server.
  • kotaemon is licensed under Apache-2.0, while local-deep-research is licensed under MIT.
  • Both can use local models or cloud providers, but local-deep-research also describes encrypted per-user databases and configurable egress scopes, with egress controls characterized as best-effort rather than a hard security boundary.
  • kotaemon requires Python 3.10 or newer for non-Docker installation; local-deep-research's fully local operation depends on suitable model-serving software and hardware.

Choose kotaemon if you…

  • need a self-hosted interface for asking questions about document collections.
  • want to customize indexing, retrieval, reasoning, or the chat UI.
  • need to inspect citations and passages while exploring PDF or multimodal document content.
Read the kotaemon analysis →

Choose local-deep-research if you…

  • want to research across web, academic services, and configured private documents.
  • need cited summaries or structured reports that can be exported as Markdown or PDF.
  • want interfaces for research through a web UI, Python or HTTP APIs, or an MCP server.
Read the local-deep-research analysis →

Compare the numbers side by side, or add more projects

This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.