About TokenVeil
TokenVeil exists because pasting sensitive data into a chat window kept bothering me at work.
Who built this
I'm Marc Bourrel, a DevOps and cloud architect based in Toulouse. For the past ten years I've worked across networks, systems, and cloud infrastructure: Kubernetes, Docker Swarm, Azure, observability stacks, security hardening. Most of that time was spent inside other companies' infrastructure, fixing the kind of problem that only shows up once something is already in production.
In early 2026 I founded Joopin's Lab to work independently on infrastructure and security projects. TokenVeil is the first product I built, and now sell through it.
Why TokenVeil
During a production reliability mission, I kept seeing the same pattern: an engineer pastes a log, a config snippet, or an error trace into Claude or ChatGPT to get help fast. Most of the time it's harmless. Sometimes it isn't: an internal IP, a client name, a token that shouldn't have been there. Nobody reads every line before hitting send.
Banning AI doesn't fix this. People route around the ban on a personal account, which is worse. TokenVeil sits between the keyboard and the model: it strips what shouldn't leave, sends the rest, and puts the real data back in the response. I built it for my own use first, then realized other teams hit the same wall.
Open source
The core of TokenVeil is open source. The code is on GitHub at github.com/Joopinhontas/tokenveil-oss, so you can check exactly how data is handled instead of taking a vendor's word for it.