How do we stop employees pasting sensitive data into AI chats?

The extension and the desktop app check the text on the device and redact personal data and secrets before it is sent, under the policy your workspace sets.

How do we govern which AI models employees use?

Routing rules say which models may answer which requests - by data boundary, region, cost or team - and every request that broke a rule is in the audit trail.

Do people need training to use it?

No. The extension and the desktop app sit under the composer people already use and show the price and the pick; nothing changes in how they work.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

Blog

Results for “webgpu”

Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.

Get the morning and evening issues

Every new post of the day, in one email. Confirmation required.

All Models LLMs Agents Research AI

#ai 750 #agents 742 #news 654 #models 638 #llm 442 #research 331 #inference 310 #benchmark 124 #open-weights 117 #safety 99 #evaluation 85 #security 60 #automation 45 #open-source 38 #reasoning 37 #aws 34 #guide 34 #optimization 34

LLMsOct 25, 20268 min read

Google Opens ML Drift for On-Device GPU Inference

Google released ML Drift, an open-source GPU engine for on-device AI. It replaces the legacy TensorFlow Lite GPU delegate and runs on diverse hardware.

From InfoQ: AI, ML and data engineering

AgentsOct 19, 202610 min read

Google releases LiteRT Tensor API for native edge model authoring

Google launched a new API to write AI models directly in C++ for edge devices. This tool allows full control over computation graphs without waiting for framework updates.

From Google AI developers blog

How this blog is made

Every post is a routed request.

Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace. Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run it yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.

Photo: Yan Krukau

For the business

What it does for the people who use AI all day.

A quote under the composer
The price before you send
The browser extension shows the cost and the router's pick on the AI sites your teams already use.
The extension
A trace with every answer
Every decision explained
Which model answered, why it won, what it cost and what the alternatives were - kept for the retention period you set.
Open a trace
Checks on the device
Safe AI at every desk
Personal data and secrets are flagged and redacted on the computer, before a message leaves it.

Results for “webgpu”

Google Opens ML Drift for On-Device GPU Inference

Google releases LiteRT Tensor API for native edge model authoring

Every post is a routed request.

What it does for the people who use AI all day.

The price before you send

Every decision explained

Safe AI at every desk

Hugging Face releases @huggingface/kernels with 200+ WebGPU kernels for local AI