What is Console
Cognipeer Console is an open-source, self-hosted AI control plane. It puts one OpenAI-compatible endpoint in front of every model provider you use, grounds answers in your own data, keeps traffic governed, and shows what happened and what it cost. This page is the map of the guide, which is organised by task.
What Console does
- Routes every model call. One OpenAI-compatible endpoint in front of hosted providers and your own GPU fleet, with dynamic routing, fallbacks, and per-tenant budgets.
- Grounds answers in your data. A knowledge engine with crawling, chunking, vector stores, and reranking, so retrieval is part of the control plane rather than bolted onto each app.
- Keeps it governed. Guardrails and PII policies on the way in and out, agent tracing for what actually happened, and spend attribution for what it cost.
Where to go
| If you want to... | Go to |
|---|---|
| Install Console and make the first request | Install and Create your first model |
| Connect providers, route and serve models | Providers and the Models and Gateway group |
| Build, publish and run agents | Agents |
| Give agents tools | Tools overview |
| Ground answers in your data | Knowledge Engine |
| Share an agent with people or embed it | Portals |
| Control who can do what, and enforce safety | Access control and Guardrails |
| See what happened and improve it | Tracing and Cost and optimization |
| Run Console in production | Deployment |
| Look up an endpoint | API reference |
| See worked examples | Use cases |
Every former how-to now lives next to the feature it covers; the Guides directory lists where each one went.