Local AI gateway
When your models, MCP services, or search provider changes, update the gateway once instead of every Agent.
In the past, switching large models—whether changing an API key or switching providers—meant updating every AI tool you were using one by one. Now, you only need to make the change in OmniProxy.
See how it worksSeeing 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 worksClassify models, filter the models available to a user based on their current device, and help users quickly find a local model that suits them among tens of thousands of open-source models.
See how it worksSet text redaction rules for each external source. When enabled, sensitive text such as passwords and phone numbers is replaced with redaction markers before being sent to the corresponding source, helping reduce the risk of privacy and confidential information leaks.
See how it worksConnect the web search service of your choice to get on-demand webpage summaries and original links, giving large models more references.
See how it worksSet a professional glossary for translation models to help translations use the industry terms you need.
See how it worksChat, image generation, text-to-speech, and video generation each have a fixed model entry point. When you want to try a new model, just change the corresponding selection in OmniProxy. AI tools keep using the original entry point, saving you the trouble of reconfiguring them.
See how it worksChecking status and adjusting settings no longer means hunting for options or looking up commands yourself every time. Let an AI tool with command execution capability do it for you through the OmniProxy command line. Hand repetitive configuration work to AI and free up time for your own tasks.
See how it worksOmniProxy.ai connects AI tools, models, and services through one gateway, bringing keys, model mapping, call logs, search, translation, and redaction together.
When switching model providers, you don't need to modify each AI tool's configuration one by one, and you don't need to scatter model keys across different tools. Connection settings are managed centrally in OmniProxy, and keys are stored in the Mac system Keychain.
Read the chat history between AI tools and models to gain a deeper understanding of how AI tools interpret tasks, organize requests, and use model responses. This helps you use AI more effectively and provides clues for troubleshooting the issues you're currently facing.
Open-source models are organized by category and filtered for what your current device supports, helping you choose faster. You can specify multiple model folders and directly use models that other tools have already downloaded, reducing duplicate downloads. You can also download models to an external drive or network drive to save local storage space.
Replace sensitive information identified by rules—such as phone numbers, bank accounts, and passwords—with xxxxxx, so that this content is not sent along with requests to remote services.
Connect a web search service so AI can access new information beyond its existing knowledge, while also providing webpage summaries and original links so you can check sources and verify the basis for answers.
Keep product names, industry terms and common expressions consistent, reducing the frustration of seeing the same word translated differently across paragraphs. Build a glossary from translations you approve and reuse it in supported translation workflows, reducing the repeated work of correcting terminology in each document.
Set fixed model entry points for purposes such as chat, text-to-image, text-to-speech, and video generation. AI tools only need to connect to the corresponding entry point. If you later want to change the model for that purpose, simply switch it in OmniProxy—no need to modify the AI tool's calling configuration.
Hand queries and settings supported by the command line to an AI tool with command execution capability, automate OmniProxy's various settings, and greatly save configuration time.
OmniProxy does not install or manage these third-party tools. Use each tool's official installer, then follow its connection guide.
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 setupWant 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 setupWant 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
