← Back to catalog Plandex · managed by DINAO

Your AI development agent, server in France

An open-source AI coding agent, terminal-based, designed for large multi-file projects. The Plandex server is installed and monitored by DINAO — hosted in France, with your own keys or models.

Server hosted in FranceTerminal modeMulti-modelGDPR CompliantOfficial publisher image
Overview

What is Plandex?

Plandex is an open-source AI coding agent, terminal-based, designed for what other tools cannot handle: large, multi-file development tasks rooted in real projects. It plans and executes changes that span many steps and affect dozens of files.

Plandex supports up to 2M tokens of direct context (~100k per file) and can index much larger directories thanks to project maps based on tree-sitter. A cumulative diff sandbox keeps AI-generated changes separate from your files until validation, and command execution is controlled for easy rollback and debugging.

Its client-server architecture separates the local CLI from the server, which manages plan orchestration, multi-file context management, versioning, and model routing. The Plandex server is open source and self-hostable, with a "bring your own key" model routing to over ten providers (Anthropic, OpenAI, Google, open source) from a single instance.

Compatible offers

Host Plandex at DINAO

Resource tiers compatible with Plandex prerequisites (minimum 2 vCPU / 2 Go / 10 Go). Hosted in France, fully managed.

Standard
2 vCPU · 4 Go · 40 Go
19,90 € /month excl. VAT
  • 2 dedicated vCPU
  • 4 Go RAM
  • 40 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Dédié
8 vCPU · 16 Go · 160 Go
79,90 € /month excl. VAT
  • 8 dedicated vCPU
  • 16 Go RAM
  • 160 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order

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.

Under the hood

Technical details

vCPU
2 vCPU
ideal : 4 vCPU
Memory
2 Go
ideal : 8 Go
Disk
10 Go
ideal : 50 Go
Image : plandexai/plandex-server:latest Registry : docker.io Services : plandex-server, plandex-postgres Ports : 8099, 4000
FAQ

You might be wondering…

Does Plandex send my code to an external service?

The Plandex server is hosted by DINAO in France, but generation requests go to the model provider you configure (your keys). To remain fully sovereign, connect a local model.

Which models can I use?

You combine models from Anthropic, OpenAI, Google, and open-source providers via your own keys (BYO), or connect a hosted local model.

How does Plandex handle large projects?

It supports up to 2M tokens of direct context and maps large repositories via tree-sitter, with a cumulative diff sandbox to safely validate changes.

Where is the server hosted?

On your DINAO instance in France, in one of the available data centers. Orchestration, context, and versioning remain on French territory.

Can I export my work?

Yes. Your plans and code remain yours and are exportable, with no proprietary lock-in; you can change tiers at any time.