Hysen Labs
Model or dataset
soapbucket/sbproxy avatar
soapbucket

sbproxy

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs. Keys, budgets, guardrails, semantic cache, WAF.

49 stars1 forksRustApache-2.0
DEEP OPEN-SOURCE ANALYSIS

sbproxy: Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs. Keys, budgets, guardrails, semantic cache, WAF.

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs.

What the project is

sbproxy is a Rust project hosted on GitHub. Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs. Keys, budgets, guardrails, semantic cache, WAF. SBproxy is a single Rust binary that puts one policy engine in front of three kinds of traffic: HTTP APIs, AI model calls across 72 native providers reaching 200+ models through one OpenAI-compatible endpoint, and MCP or agent-to-agent tool calls. All three run through the same request pipeline, so a rate limit, a guardrail, a budget cap, and an audit record behave the same way no matter which traffic type triggered them. Every feature in this repository ships under Apache-2.0. The repository is maintained by soapbucket and tracks activity through its public issue tracker and commit history. Readers who want a working example rather than a bare library will find the documentation and the linked resources useful for getting a first build running.

What it offers

The sbproxy README focuses on describing the project behaviour and its intended audience instead of a long feature checklist. The description and the introductory sections explain what the tool does and which problems it addresses. Browsing the source tree shows the modules and sample files that make up the actual implementation.

How to set it up

Getting sbproxy running starts with cloning the source from https://github.com/soapbucket/sbproxy. The README lists the commands needed to fetch the code and build or launch it. Representative steps from the documentation include: curl -fsSL https://download.sbproxy.dev | sh git clone https://github.com/soapbucket/sbproxy brew install soapbucket/tap/sbproxy docker pull soapbucket/sbproxy:latest. After the code is on disk, the project instructions walk through configuration and any dependencies. Following the order shown in the README avoids the common setup mistakes that come from mixing steps.

License and project status

sbproxy is written primarily in Rust and is released under the Apache-2.0 license, which sets the terms for reuse and redistribution. The project reports around 49 stars on GitHub, a signal of how many developers have bookmarked it. The source was last updated on 2026-08-21. The canonical location is https://github.com/soapbucket/sbproxy, where the license file, the changelog and the open issues give the most current state of the work. Anyone planning to depend on it should read the license text directly before shipping it inside another product.

Editorial conclusion

The sbproxy source lives at https://github.com/soapbucket/sbproxy under the Apache-2.0 license and is mainly written in Rust. The README and the linked examples remain the place to confirm the current behaviour before adopting the project.

DEEP OPEN-SOURCE ANALYSIS

Official sources

Community notes

Community notes