Create unlimited AI Chatbot Agents for your websites

Qarīn.ai lets you create unlimited AI chatbot agents for your websites — no coding required.
It works with any LLM provider that supports the OpenAI-Compatible API, including self-hosted providers like llama.cpp or Ollama.

With Qarīn.ai, you can:

• Define an agent's name, identity, and instructions.
• Instantly generate a chat bubble widget to embed on your site.
• Enhance agents by connecting to MCP Servers or importing your own API specs.
• Build vector stores from documents for retrieval-augmented generation (RAG).
• Expose vector stores or MCP Servers to external AI agents.

• No Coding Needed!
• Supports RAG & MCP out of the box.
• Works with any OpenAI-Compatible LLM provider (including self-hosted).
• One-click MCP Server generation from existing REST API specs (Swagger/OpenAPI).
• Native vector storage with optional MCP Server exposure for each store.
• Easy-to-use chat bubble widget for quick website integration.
• Simple Docker or Kubernetes deployment.

Requirements

• Docker & Docker Compose installed.

Run Qarīn.ai

git clone https://github.com/qarinai/qarinai.git
cd qarinai
docker compose up -d

This starts Qarīn.ai with all required environment variables pre-configured.

• Username: admin
• Password: admin

Once running:

1. Connect your desired LLM provider (OpenAI, Ollama, llama.cpp, etc.).
2. Select the models you want to use.
3. Set a default model for minor app tasks (summarization, descriptions, etc.).
4. (Optional) Import MCP Servers into Qarīn.ai.
5. (Optional) Import Swagger/OpenAPI specs to auto-generate MCP Servers.
6. (Optional) Create vector stores and upload documents for RAG.
7. Create your AI agent — define name, identity, and instructions.
8. Embed it — click “Add to Website” to get your dynamic snippet code.

Qarīn.ai is still in active development — several existing features are only partially implemented or missing certain CRUD operations and use cases.
The near-term focus will be completing and stabilizing all current functionality before expanding further.

Planned enhancements:

• 🛠 Complete existing CRUD operations and missing use cases for certain resources.
• 🔒 Enhanced security:
  • User management with multiple accounts and ACL (Access Control Lists).
  • Personal Access Tokens with scopes instead of full unrestricted access.
  • Secure the public bubble APIs.
• 📊 Conversation tracking UI:
  • Visual interface to inspect each conversation and message per agent (currently only stored in DB).
• 🎨 Agent UI customization:
  • Style, color, and branding customization for the chat bubble and iframe widget.
• 🚀 Additional quality-of-life improvements after stabilization.

This project is licensed under the Apache 2.0 License — see LICENSE for details.

Qarīn.ai would not have been possible without the incredible work of the open-source community.
This project stands on the shoulders of countless developers and contributors who make their tools, libraries, and frameworks available for everyone to learn from and build upon.

A special thanks to the maintainers of the amazing technologies powering Qarīn.ai, including (but not limited to):

• Frontend & UI: Angular, PrimeNG, TailwindCSS, ngx-markdown
• Backend & APIs: NestJS, @modelcontextprotocol/sdk, OpenAI SDK, Zod
• AI & NLP: @huggingface/transformers, @langchain/textsplitters
• Database & Storage: TypeORM, PostgreSQL, pgvector
• Build & Tooling: Webpack, Gulp, Docker
• And many more... — every dependency plays a role in making this project possible.

If you maintain one of these libraries: thank you for your dedication to open-source! ❤️

Contributions are not open at the moment as the project is still in an early stage.
However, suggestions and feedback are welcome — feel free to open an issue or discussion.