01
Change a model key and update every single AI tool?
In the past, switching LLMs—whether updating an API key or changing providers—meant modifying every active AI tool one by one. Now, you only need to update it once in OmniProxy.
See how it worksLet every Agent connect only to OmniProxy.ai
Local AI gateway
When your models, MCP services, or search provider changes, update the gateway once instead of every Agent.
AI tools and Agents
OpenClawCursorOpenCodeCodex CLI+ more AI tools
AI resources
Local modelsCloud modelsMCP servicesSearch
- 02
What secret conversations are your AI tools and models having?
Seeing the details of each exchange between an AI tool and a model is an effective way to learn how AI works. When you give an AI tool a task, you usually see only part of the model’s response. Open OmniProxy to see how the tool and model communicate.
See how it works - 03
With so many models, which one should I deploy?
Models are organized by category and filtered for what your current device can run, helping you quickly find a suitable local model among tens of thousands of open-source models.
See how it works - 04
Protect your privacy and confidential information
Set text redaction rules for each external source. Once enabled, sensitive text such as passwords and phone numbers will be replaced with redaction markers before being sent to that source, helping reduce the risk of privacy and confidential data leaks.
See how it works - 05
Find information beyond model knowledge
Connect your chosen web search service to retrieve on-demand web page summaries and original links, providing more reference context for large language models.
See how it works - 06
Give translation models a professional glossary
Set up a professional glossary for translation models to help translations use the industry terms you need.
See how it works - 07
Switch models anytime, keep using your tools as usual
Maintain dedicated fixed model entries for chat, image generation, text-to-speech, and video generation. Want to try a new model? Simply switch the selection inside OmniProxy while your AI tools keep using their existing endpoints, saving you the hassle of reconfiguring them.
See how it works - 08
Leave configuration tasks to AI
Checking status and adjusting settings doesn't require digging through options or commands yourself every time. Let command-capable AI tools handle it for you via the OmniProxy CLI, delegating repetitive setup work to AI so you can focus on your own priorities.
See how it works
Manage models and related services in one place
OmniProxy.ai connects AI tools, models, and services through one gateway, bringing keys, model mapping, call logs, search, translation, and redaction together.
Centralize remote model settings and API keys
When switching model providers, you no longer need to update each AI tool’s configuration individually or keep model keys scattered across different tools. Manage connection settings centrally in OmniProxy and leave your keys in the Mac’s system Keychain.
Log every interaction between AI tools and models
Review detailed interaction logs between AI tools and models to gain deep insight into how tools interpret tasks, structure requests, and utilize model responses. This helps you use AI more effectively and provides clues for troubleshooting issues.
Deploy local models with ease
Browse open-source models by category and filter for those your current device supports to make your choice faster. Specify multiple model folders and directly use models already downloaded by other tools, reducing duplicate downloads. You can also download models to an external drive or network drive to save local storage space.
Redact sensitive information before sending to remote models
Replace sensitive details identified by rules—such as phone numbers, bank account numbers, and passwords—with xxxxxx before sending requests, preventing this content from being sent to remote services.
Supplement models with web context
Integrate a web search service to allow AI to retrieve new information beyond its existing knowledge base, providing web page summaries and original links so you can inspect sources and verify response accuracy.
Provide professional glossaries for translation
Keep product names, industry terms, and common expressions consistent, avoiding confusing variations of the same word across paragraphs. Accumulate approved translations into a glossary and reuse them across supported translation workflows to reduce repetitive manual corrections.
Customize model endpoints by use case
Set fixed task entries for chat, text-to-image, text-to-speech, and video generation. AI tools simply connect to their designated endpoint; whenever you want to change the underlying model for a use case, switch it inside OmniProxy without modifying tool calling configurations.
Let AI tools manage OmniProxy for you
Delegate queries and settings supported by the command line to AI tools that can execute commands. Automate OmniProxy settings and greatly reduce the time you spend on configuration.
Tools whose AI model you can choose
OmniProxy does not install or manage these third-party tools. Use each tool's official installer, then follow its connection guide.
Chat
Open WebUI
Want to use local and cloud models in the same chat window but are concerned that deployment and connection setup will be too complicated? Open WebUI provides a familiar chat interface. Once installed, you can start using it by entering the connection details step by step.
Read installation and setupAgent
goose
Want an AI assistant that can read files, write content, or handle repetitive tasks without being limited to a web browser? goose offers both desktop and terminal versions. Once installed and configured with a model, it is ready to use on your own computer.
Read installation and setupAgent
OpenClaw
Want to install an AI assistant on your own computer but are concerned about setting up the environment or switching models? OpenClaw provides a desktop app and installation scripts, allowing you to use it from a messaging app or terminal after installation.
Read installation and setup