Build Your Mixture-of-Models
vLLM Semantic Router is an open-source routing layer for heterogeneous large language model inference. It classifies requests using signals such as intent, safety, and domain, then directs them to suitable models with observable decisions and vLLM deployment support.
Open SourceApache-2.0WebCLICloud-managedSelf-hosted
5.1kstars
801forks
1alternative
10features
2025since
Overview
10 featuresIn the Autonomous agents & workflows space, Build Your Mixture-of-Models takes a focused approach. It focuses on choosing and operating the right language model for each request across a heterogeneous model fleet. Build Your Mixture-of-Models is an open-source project aimed at AI infrastructure engineers and developers. Build Your Mixture-of-Models is open source under the Apache-2.0 license. It ships for the web and the command line, and it can be self-hosted.
vLLM Semantic Router builds and maintains Build Your Mixture-of-Models, and it first shipped in 2025. Development happens publicly on GitHub with 5.1k stars and 409 commits in the last 90 days. Key capabilities include mixture-of-models routing, signal-based classification, and intent routing. The interface is available in English and Chinese.
Summary written by a language model from the project’s public pages.
- Mixture-of-models routing
- Signal-based classification
- Intent routing
- Safety routing
- Domain routing
- Model fleet management
- Decision observability
- Hallucination detection
- Playground
- vLLM endpoint
Tags
llm-routingmixture-of-modelsvllm-inferencehallucination-detectionmodel-orchestration
AI capabilities
TextStructured
Inference: Cloud API
Built with & integrations
Hosting
Netlify
AI providers
local_ossmultiple
Connectors
github
Runs on
BrowserCLICloud-managedSelf-hosted
Detected from
- Netlify
- x-nf-request-id header
- local_oss
- bvllm in the HTML
Trust & compliance
License
Apache-2.0
Verified signals
HTTPSOpen SourceFree tierActive maintenanceMulti-language
Indexing history
1What PulseGate has recorded for this listing
- Indexed6 Aug · 20:03 UTCLettuceDetect v2 in Semantic Router: Gen. Hallucination Detection vLLM Endpoint verified against its public sourceSource: PulseGate · Open
Frequently asked questions about Build Your Mixture-of-Models
- What does Build Your Mixture-of-Models do?
- Build Your Mixture-of-Models focuses on choosing and operating the right language model for each request across a heterogeneous model fleet. It is catalogued under Autonomous agents & workflows on PulseGate.
- Who is Build Your Mixture-of-Models for?
- Build Your Mixture-of-Models is an open-source project built for AI infrastructure engineers and developers.
- Is Build Your Mixture-of-Models free?
- Yes — Build Your Mixture-of-Models is open source under the Apache-2.0 license and free to use.
- What platforms does Build Your Mixture-of-Models run on?
- Build Your Mixture-of-Models runs on the web and the command line. It can also be self-hosted.
- Is Build Your Mixture-of-Models still active?
- The GitHub repository shows 409 commits in the last 90 days.
- Who makes Build Your Mixture-of-Models?
- Build Your Mixture-of-Models is developed by vLLM Semantic Router.
- How long has Build Your Mixture-of-Models been around?
- Build Your Mixture-of-Models first shipped in 2025.
- Is Build Your Mixture-of-Models open source?
- Yes — Build Your Mixture-of-Models is open source under the Apache-2.0 license.
Similar projects
Closest matches by what these projects do