Security
Your design never leaves your network
Red Chili runs on premises, in your environment. It makes no model calls, needs no external backend and works fully air-gapped.
Runs on your machines
Red Chili is installed inside your network, next to your repositories and EDA flows. There is no Chilicon cloud service behind it.
Makes no model calls
Red Chili itself calls no language model. Your coding agent keeps talking only to the model your company already approved.
Works air-gapped
Nothing is sent out: no design data, no usage data, no telemetry. It runs the same with no internet connection at all.
Your project stays yours
What Red Chili knows about your design lives in your installation. Each project is kept separate, and you decide what, if anything, is shared with us.
Every fact has a source
Each fact in a briefing points back to the file, result or decision it came from, so engineers and reviewers can check it.
What runs where
- Red Chili
- Your machines, inside your network.
- Your coding agent and its model
- Whatever your company already uses and approved. Red Chili adds no model of its own.
- Your RTL, specs and results
- Your repositories and servers, as today. Red Chili reads them in place.
- Chilicon
- No access to your environment unless you grant it, for example during a pilot.
Security questions or a review checklist from your team? We answer them before any pilot starts. Contact us
Built for agent-driven chip design
As chip design becomes agent-driven, Red Chili helps the engineering infrastructure evolve with it. We’re opening pilots for RTL and DV teams already using coding agents.
Request a Pilot