← Back to catalog GPT-Researcher · managed by DINAO

Your AI research agent, hosted in France

The autonomous agent that conducts online research and writes sourced reports, powered by GPT-Researcher, installed and maintained by DINAO. Your topics and reports stay on our French servers — and in local mode, your AI never leaves France.

Hosted in FranceGDPR CompliantAutonomous SearchSourced ReportsOfficial publisher image
Overview

What is GPT-Researcher?

GPT-Researcher is an autonomous AI agent dedicated to online and local documentary research. Starting from a simple question, it plans its approach, queries the web or your documents, aggregates numerous sources, and synthesizes a detailed, objective, and structured report — all without continuous human intervention.

Its multi-agent architecture (one agent that plans, agents that execute and collect) allows it to cross-reference dozens of sources per search, which reduces bias and improves factual accuracy. Each report cites its sources and can be exported in Markdown, PDF, or Word.

Regarding models, GPT-Researcher is agnostic: it can rely on an external API (OpenAI, Anthropic, Mistral…) or on a locally hosted open-weight model. It supports RAG on your documents, on the web, or in hybrid mode. Distributed under the Apache 2.0 license, it integrates via an API and a web interface.

Compatible offers

Host GPT-Researcher at DINAO

Resource tiers compatible with GPT-Researcher prerequisites (minimum 1 cœur / 1 Go / 5 Go). Hosted in France, fully managed.

Découverte
1 vCPU · 2 Go · 20 Go
9,90 € /month excl. VAT
  • 1 dedicated vCPU
  • 2 Go RAM
  • 20 GB NVMe
  • Daily backups
  • Managed & monitored by DINAO
Order
Performance
4 vCPU · 8 Go · 80 Go
39,90 € /month excl. VAT
  • 4 dedicated vCPU
  • 8 Go RAM
  • 80 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
🧠

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
1 cœur
ideal : 2 cœurs
Memory
1 Go
ideal : 4 Go
Disk
5 Go
ideal : 20 Go
Image : gptresearcher/gpt-researcher:latest Registry : docker.io Services : gpt-researcher Ports : 8000
FAQ

You might be wondering…

What does GPT-Researcher do?

It is an autonomous AI agent that, starting from a question, plans its research, queries the web (or your documents), aggregates numerous sources, and writes a detailed, objective, and sourced report.

Are my searches confidential?

On your DINAO instance, queries and reports remain in France. In local LLM mode, inference is done on-site: no content is sent to an external AI provider.

Can I search within my own documents?

Yes. GPT-Researcher can perform RAG on your documents, on the web, or combine both, to produce reports grounded in your own sources.

Which models can I use?

A locally hosted open-weight model (sovereign mode), or an external API (OpenAI, Anthropic, Mistral…) with your own key. The choice depends on your confidentiality requirements.

In what format are reports provided?

In Markdown, PDF, or Word, with their sources cited. Reports can be short or detailed depending on the requested search mode.