PrivateGPT
PrivateGPT is Zylon's open-source API layer for private AI applications: retrieval over your documents, skills, tools, MCP and text-to-SQL, behind an OpenAI-compatible server you host yourself. Its docs include an Opper provider page, so you set Opper as the OpenAI base URL, pick a chat model and an embedding model, and your documents stay on your own infrastructure while inference runs on any of 700+ models, with EU-hosted routes available.
PrivateGPToninConnect PrivateGPT to Opper
Set up with agents
Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.
Run PrivateGPT across our providers
On Opper, PrivateGPT can reach every provider in the catalogue. Pick where your inference runs, keep it in the EU when you need to, and use zero data retention on supported routes.
More apps on Opper
RAGFlow
The open-source RAG engine with deep document understanding. Add Opper as a model provider and its chat, embeddings and agents run on one key.
Opper built in
Claude Code
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claudeClaude Cowork
Anthropic's desktop agent for knowledge work. Run it on any model on Opper, not just Claude.
Anthropic-compatible