kotaemon
Open-source RAG web app for chatting with your documents, with citations and GraphRAG.
Quick answer
kotaemon is an open-source RAG web app for chatting with your documents, with citations and GraphRAG, listed under Knowledge base & RAG. A typical small-business use: q&A over internal manuals, contracts or reports with page-level citations. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: Apache-2.0, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 23, 2026.
What is kotaemon?
kotaemon is a Gradio-based web UI for question answering over your own documents. It supports hybrid (full-text plus vector) retrieval with re-ranking, multi-modal parsing of figures and tables, citations with in-browser PDF previews, and GraphRAG-style indexing (NanoGraphRAG, LightRAG, MS GraphRAG). It works with API providers such as OpenAI, Azure, Cohere and Groq or with local models through Ollama and llama-cpp-python, and has multi-user login with private and public collections.
Where it fits in a 10–200 person business
- Q&A over internal manuals, contracts or reports with page-level citations
- Private document chat on local models using the image with bundled Ollama
- Team knowledge base with shared and private document collections
These use cases are our editorial suggestions, not claims made by the project.
Can a business use kotaemon? (license)
| License | Apache-2.0 |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep license and notices. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does kotaemon phone home?
| Telemetry (usage data sent to the vendor) | Not documented |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Not documented |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does kotaemon need?
The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.
No official hardware requirements published. The README lists Python 3.10+ (or Docker) and, for extra file types, Unstructured. With local models, needs depend on the Ollama or llama.cpp model you choose.
How much does it cost to host kotaemon per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy kotaemon
Method: Docker
docker run \
-e GRADIO_SERVER_NAME=0.0.0.0 -e GRADIO_SERVER_PORT=7860 \
-v ./ktem_app_data:/app/ktem_app_data \
-p 7860:7860 -it --rm \
ghcr.io/cinnamon/kotaemon:main-lite
# open http://localhost:7860 (main-full adds Unstructured, main-ollama bundles Ollama) From the official instructions: github.com/Cinnamon/kotaemon#readme. Always check the source for the current version before you run it.
Known gotchas when self-hosting kotaemon
- The default username and password are both admin. Change them before exposing the app; the initial admin account comes from KH_FEATURE_USER_MANAGEMENT_ADMIN and KH_FEATURE_USER_MANAGEMENT_PASSWORD. source
- The .env file is only read once to populate the database on the first run. Later model or API-key changes must be made in the Resources tab of the UI. source
- The lite image only handles .pdf, .html, .mhtml and .xlsx well; .doc, .docx and other types need the larger main-full image (Unstructured). source
- Official MS GraphRAG indexing only works with the OpenAI or Ollama API; the maintainers recommend NanoGraphRAG for most users. source
Alternatives in Knowledge base & RAG
- RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare kotaemon vs RAGFlow
- AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs kotaemon
- PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare kotaemon vs PrivateGPT
- Open Notebook Private, self-hosted alternative to Google NotebookLM with your choice of AI models. Compare kotaemon vs Open Notebook
- Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare kotaemon vs Onyx (formerly Danswer)
- FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs kotaemon
- MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare kotaemon vs MaxKB
kotaemon FAQ
How much RAM does kotaemon need?
kotaemon does not publish an official RAM figure, so we do not state one. The README lists Python 3.10+ (or Docker) and, for extra file types, Unstructured. With local models, needs depend on the Ollama or llama.cpp model you choose.
How much does it cost to self-host kotaemon?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is kotaemon free for commercial use?
kotaemon is licensed under Apache-2.0 (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep license and notices. This is a summary, not legal advice.
What are common problems when self-hosting kotaemon?
The default username and password are both admin. Change them before exposing the app; the initial admin account comes from KH_FEATURE_USER_MANAGEMENT_ADMIN and KH_FEATURE_USER_MANAGEMENT_PASSWORD. The .env file is only read once to populate the database on the first run. Later model or API-key changes must be made in the Resources tab of the UI. The lite image only handles .pdf, .html, .mhtml and .xlsx well; .doc, .docx and other types need the larger main-full image (Unstructured). Official MS GraphRAG indexing only works with the OpenAI or Ollama API; the maintainers recommend NanoGraphRAG for most users.
Is kotaemon still maintained?
Yes, it is actively developed. Last commit: May 30, 2026. Latest release: v0.12.0 (May 31, 2026). Checked Oct 23, 2026.
How do I install kotaemon?
The official method is Docker. The exact commands are in the "How to deploy" section above and in the official instructions: https://github.com/Cinnamon/kotaemon#readme
What are self-hosted alternatives to kotaemon?
Other apps in Knowledge base & RAG: RAGFlow, AnythingLLM, PrivateGPT, Open Notebook, Onyx (formerly Danswer), FastGPT, MaxKB.
Sources
- GitHub repository: github.com/Cinnamon/kotaemon
- Official documentation: cinnamon.github.io/kotaemon/
- License text: github.com/Cinnamon/kotaemon/blob/main/LICENSE.txt
- Hardware requirements, Deploy instructions, Gotcha 2, Gotcha 3, Gotcha 4: github.com/Cinnamon/kotaemon#readme
- Gotcha 1: github.com/Cinnamon/kotaemon/blob/main/flowsettings.py
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-23. Spotted something out of date? Tell us.