Vidai launches in-network AI call governance control room
Start here
Vidai has launched a Control room that governs every AI call inside a customer's own network, checking caller identity, prompt contents, and permitted models and regions before routing, pricing, and signing a record of each request. It works with the OpenAI, Anthropic, and Gemini SDKs through a single configuration change. Vidai reports 47,200 calls a second on one machine with 0.58 ms median added latency. The product is free with no expiry for engineers trying it on their own traffic, with commercial use requiring approval. Bedrock and Vertex AI providers are in alpha. Vidai says that after a 20-minute demo it agrees a two-week pilot covering one app or team, the customer's traffic, and the customer's infrastructure.
Generated from reports · updated 14 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIVidai launches AI governance control room that inspects every model call
Vidai has introduced a Control room that governs every AI call inside a customer's own network, checking caller identity, prompt contents and permitted models and regions before routing, pricing and signing a record of each request. It works with OpenAI, Anthropic and Gemini SDKs through a single configuration change, and Vidai reports 47,200 calls a second on one machine with 0.58 ms median added latency.
Heat for this event
- Current, comparable range
- 7
- Peak, comparable range
- 10November 17 18:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.