Build your custom AI agent in France
A production-ready AI agent framework powered by Cheshire Cat AI, installed and maintained by DINAO. RAG, memory, plugins, and tools — build your assistant on your French servers.
What is Cheshire Cat AI?
Cheshire Cat AI is a production-ready AI agent framework designed to build custom artificial intelligences on top of any language model. The authors compare it to tools like WordPress or Django : a reusable foundation, but specifically designed for AI.
The framework is API-first : chat via WebSocket, customizable REST API, integrated RAG based on the Qdrant vector database, extensibility via plugins, event callbacks, function calling (tools), and conversational forms. It offers a user-friendly admin panel, multi-user support with granular permissions, and compatibility with any language model via LangChain.
Fully dockerized and supported by an active community, Cheshire Cat AI is easy to install and operate, while remaining open and extensible to adapt to your business use cases.
Host Cheshire Cat AI at DINAO
Resource tiers compatible with Cheshire Cat AI prerequisites (minimum 2 vCPU / 4 Go / 20 Go). Hosted in France, fully managed.
- 2 dedicated vCPU
- 4 Go RAM
- 40 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 4 dedicated vCPU
- 8 Go RAM
- 80 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 8 dedicated vCPU
- 16 Go RAM
- 160 GB NVMe
- Daily backups
- Managed & monitored by DINAO
1 hidden tier(s) (insufficient resources for this app) : Découverte
This application uses AI
The container hosts the application, not the AI engine (which requires dedicated GPUs) : inference is handled externally, with your own provider key. Prioritize a sovereign engine — Mistral AI, NumSpot, Scaleway, or OVHcloud AI Endpoints (France, GDPR) ; an international provider (OpenAI, Anthropic…) only if a specific capability requires it. Inference subscriptions are not included in hosting.
Technical details
You might be wondering…
What is Cheshire Cat AI used for?
It is a framework for building custom AIs on top of any language model : imagine an « AI WordPress », with RAG, memory, plugins, and tools, to create your own business assistant.
Can I query it on my own documents?
Yes. The native RAG (Qdrant vector database) allows the agent to respond based on your documents, with memory of exchanges.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available data centers. In local mode, your data does not leave the territory.
Are technical skills required?
Using the assistant is simple, but building and extending the agent (plugins, tools) requires a technical profile. DINAO manages installation, security, and updates.
Can I connect my own models?
Yes. Cheshire Cat is compatible with any LLM via LangChain : a local open-weight model hosted on your instance, or an external API with your key.