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

Pricing
Blog

OpenSmartRoute

Site footer

The right AI model for every request. Cheaper, safer and explained.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0Platform v2.1.0 developer preview 2.1.0-preview.109enterprise edition

The daily newsletter

Models, LLMs and agents, one email a day. Confirm by email; leave with one click.

Email address

Product

Models
Routing lab
Playground
Marketplace
Services
Browser extension
Desktop app
VS Code extension
Security
Observability
Pricing

Solutions

Who it is for
Budget owners
Platform teams
Security teams
Developers
Enterprise
Bring your bill
ROI calculator
Run a pilot
Benchmark
Compare

Industries

All use cases
Customer support
Coding
Financial services
Healthcare
Legal
Retail and marketing
Rules by industry

Developers

SDKs and API
Migrate in one line
Coding agents and tools
Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Self-hosting

Open source

Downloads
Changelog
Open Capability Manifest
Agent skills
PyPI
npm

Company

Blog
Newsletter
What is live
Status
Proof and who runs this
Trust and SLA
Support
Contact sales

Learn

AI routing
Why an AI router
LLM router
AI model router
AI gateway
Automatic model selection
AI model abstraction layer
Open-source LLM router
LLM cost optimization
AI agent routing
AI governance
Shadow AI
MCP router
Enterprise AI router
Glossary

Terms Privacy Cookie settings Trust Report a vulnerability

Support assistant

Answers from the documentation; checking which model is on duty

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Support assistant

Answers from the documentation; checking which model is on duty

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Blog

Results for “tools”

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.

Email address

All Models LLMs Agents Research AI

Search posts

RSS

#ai 736 #agents 735 #news 653 #models

AIOct 2, 20268 min read

Sean Parker rebuilds Stability AI focused on music AI tools

Sean Parker has taken a leading role in rebuilding Stability AI, now focusing on AI tools for music professionals, with new funding and models announced.

From TechCrunch AI

AIOct 2, 20269 min read

MIT develops reinforcement learning tools for complex societal challenges

MIT researchers use reinforcement learning to improve transportation systems and address complex societal problems.

From MIT News: artificial intelligence

Airbnb adopts inside-out AI to transform product development and guest services

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.

634

AgentsOct 2, 20269 min read

Airbnb adopts inside-out AI to transform product development and guest services

Airbnb is using AI internally to speed up product creation and improve guest experiences, with new tools and models deployed at scale.

From Latent Space

LLMsSep 30, 20261 min read

Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages

Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data. Regional dialects and...

From NVIDIA technical blog

LLMsSep 30, 20262 min read

Deploying HSTU Generative Recommender with NVIDIA Dynamo-Triton

NVIDIA now supports an end-to-end workflow for deploying HSTU generative recommender models using Dynamo-Triton. It improves latency and efficiency.

From NVIDIA technical blog

AISep 30, 20261 min read

Flow Engineering raises $50M at $750M valuation for AI hardware design tools

Flow Engineering, a startup offering AI tools for hardware design, raised $50 million in a Series B round. The valuation reached $750 million.

From TechCrunch AI

AISep 30, 20264 min read

Empower your agents with the Google Cloud CLI remote MCP server

Today, we’re expanding our ecosystem of managed remote MCP servers by introducing the Google Cloud CLI remote MCP server in preview. Powered by the popular gcloud and bq (BigQuery) command-line tools, this new server gives AI agents imme...

From Google Cloud AI blog

AgentsSep 30, 20262 min read

OpenAI DevDay 2026 introduces Dots, GPT-6.1 Sol, and platform updates

OpenAI announced new tools and models at DevDay 2026, including always-on agents, a new GPT-6.1 Sol model, and platform improvements for speed and safety.

From Latent Space

LLMsSep 29, 20262 min read

NVIDIA NeMo Relay now traces Hermes Agent behavior with detailed logs

NVIDIA NeMo Relay captures lifecycle events and trajectories for Hermes Agent runs. It helps analyze model and tool calls, errors, and performance.

From NVIDIA technical blog

LLMsSep 29, 20261 min read

NVIDIA TensorRT Model Connect now supports 128 model families as of 2026

NVIDIA released TensorRT Model Connect, an open source project for AI model development. It supports 128 model families tested on NVIDIA GB300.

From NVIDIA technical blog

AISep 29, 20262 min read

OpenAI launches persistent GPT-6 Astra agents called dots that run on their own cloud computers

OpenAI introduced dots, persistent AI agents powered by GPT-6 Astra. They operate continuously on dedicated cloud computers across many apps.

From MarkTechPost

AISep 29, 20261 min read

OpenAI launches Space and Pages for office work

OpenAI announced new office tools called Space and Pages at its Dev Day.

From TechCrunch AI

AISep 29, 20261 min read

OpenAI gives Codex reusable cloud environments that work across devices

OpenAI is expanding Codex with reusable cloud development environments, a revamped CLI with voice controls, new code review tools and a security-focused product for scanning repositories and preparing fixes.

From TechCrunch AI

AISep 29, 20262 min read

OpenAI adds app-like interfaces and automations to ChatGPT plugins

OpenAI now allows developers to create app-like experiences within ChatGPT using plugin extensions. These include interactive panels and file viewers.

From TechCrunch AI

AgentsSep 29, 20262 min read

Prompt engineering with Amazon Quick components improves results and reduces errors

Amazon Quick offers tools for prompt engineering across research, workflows, and analytics. Proper prompt design enhances output quality and efficiency.

From AWS machine learning blog

AISep 29, 20261 min read

Google Research Open-Sources RRSI: AI Agents That Improve Their Own Harness Without Overfitting

Google Cloud AI Research has open-sourced RRSI, a framework that lets LLM agents rewrite their own prompts, tools and memory while model weights stay frozen. It adds a leakage critic, a noise floor, a cost rule and pruning so gains carry...

From MarkTechPost

AgentsSep 29, 20262 min read

Anthropic updates Claude Code with Projects, Mods, and collaborative agent tools

Anthropic released Claude Code updates including Projects for managing conversations and Claude Mods for customization. New tools support multiplayer workflows and improve agent collaboration.

From Latent Space

The NVIDIA Open Agent Safety Platform combines the OpenShell runtime on the Vera CPU with NVIDIA Sentry running in silicon on BlueField-4. The runtime orchestrates the agent sandbox and policies, whil

LLMsSep 28, 20261 min read

NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring

To understand where agentic AI stands today, consider the last seismic shift in technology: the rise of the internet in the 90s. It was new and full of...

From NVIDIA technical blog

Three AI agents above a layered runtime stack with glowing green control icons, enclosed by a black-and-yellow safety barrier.

LLMsSep 28, 20261 min read

Add Runtime Controls to AI Agents with NVIDIA OpenShell

AI agents can be given a goal, write code, use tools, and keep working as new information becomes available. This opens the door to applications that...

From NVIDIA technical blog

NewerPage 2 of 9Older

Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.

Archive (100)

The desktop app

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.

Results for “tools”

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