Kotaemon

A clean, customizable RAG interface for asking questions about your documents, with citations shown in an in-browser PDF viewer.

25.8k stars, 2.2k forks Python On GitHub since March 2024

Visit website View on GitHub How to run it

What is Kotaemon?

Kotaemon serves two audiences. End users get a simple web interface to upload documents and ask questions, with answers that cite their sources and highlight the passages in a built-in PDF viewer. Developers get a framework for building their own RAG pipelines: the default pipeline combines full-text and vector search with re-ranking, and GraphRAG variants are supported. It works with hosted model APIs such as OpenAI, Azure OpenAI and Cohere, and with local models through Ollama or llama-cpp-python.

Good fit if

  • You want to check exactly where an answer came from in a long PDF.
  • You are prototyping a RAG pipeline and want a ready interface around it.

Look elsewhere if

  • You need an actively maintained tool: there were no commits in the last 90 days. RAGFlow and AnythingLLM are busy.
  • You want a full team platform with permissions: Onyx.

Before you adopt it

Kotaemon is Apache-2.0, published by Cinnamon AI, with no paid parts. Development appears to have stopped, so treat it as a working base you may have to maintain yourself.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Kotaemon health: is it still maintained?

17 of 100, actively developed

  • Activity
    No commits in the last 90 days, the latest on 30 May 2026.
    0 / 30
  • Contributors
    Nobody committed in the last 90 days.
    0 / 20
  • Releases
    4 releases in the last 12 months; the latest, v0.12.0, on 31 May 2026.
    12 / 20
  • Replies to issues
    Maintainers answered 0% of recent issues.
    0 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

Kotaemon license: is it open source?

Kotaemon uses Apache-2.0, an open-source license approved by the OSI.

  1. March 2024First published on GitHub.
  2. TodayApache-2.0.

How to run Kotaemon yourself

Docker
Dockerfile or compose file in the repository
Compose file
None in the repository
Setup effort
Not rated: no compose file to judge from
Kubernetes
No Helm chart in the repository
Desktop and mobile
No app builds in GitHub releases
Interface languages
English only

Install instructions: cinnamon.github.io or the README on GitHub.

Alternatives to Kotaemon

  • MaxKBMaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 82 health · GPL-3.0 · 23.1k stars
  • Open WebUIUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) 76 health · Open WebUI License · 157k stars
  • AnythingLLMStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first… 94 health · MIT · 67.8k stars
  • RAGFlowRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG… 93 health · Apache-2.0 · 93.3k stars
  • OllamaGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. 89 health · MIT · 186k stars

All 36 projects in AI chat & local LLMs

Questions about Kotaemon

Is Kotaemon open source?

Yes. Kotaemon is published under Apache-2.0, an OSI-approved open-source license.

Is Kotaemon still maintained?

Its health score is 17 of 100 (actively developed). It had no commits in the last 90 days, the latest on 30 May 2026, and its latest release came out on 31 May 2026.

How do I run Kotaemon?

You can run it with Docker. The README on GitHub has the exact steps.

What are the alternatives to Kotaemon?

Close alternatives in the AI chat & local LLMs category include MaxKB, Open WebUI, AnythingLLM.