Show HN: Aitori, see and govern the AI traffic leaving your machine

[deeptishukla22]

Hi HN, I work at TrueFoundry.

We built Aitori because AI traffic is getting harder for companies to control.

When developers call an LLM API directly, the request can be routed through a gateway. But tools like Claude Desktop, ChatGPT app, claude.ai call the model from the vendor’s backend. There is no endpoint setting you can point to your proxy.

Aitori is an open-source local proxy that runs on the employee’s machine and intercepts traffic to selected AI applications.

It uses a per-device CA, similar to mitmproxy, to inspect model and MCP requests and forward them to a gateway. Traffic to other applications is left untouched.

Once you can see the traffic, it stops being a black box. You can log it, apply policy, route it, or do whatever else you would with AI traffic you control.

It's Apache-2.0, and the forwarding contract is documented so it works with any gateway, not just ours: https://github.com/truefoundry/aitori/

Try it: curl -fsSL https://raw.githubusercontent.com/truefoundry/aitori/main/in... | sh then sudo aitori up --ui

Around all day to answer any questions.

[the_bigfatpanda]

This is pretty useful, am I right in assuming that this currently will not track payloads sent to MCP servers talking to Claude over stdio (Claude-> Stdio -> MCP Process -> Network)?

If yes, that might be an interesting problem to solve right? Given that MCP server itself could be sending data out to server to do something.

[nirali-shekhwa]

Curious how this handles apps that do certificate pinning: does it just fail closed and pass that traffic through unclassified, or is there a workaround?