Launching today
ARBR
Control Every AI Request
11 followers
Control Every AI Request
11 followers
AI stacks are getting more complex with more models, providers, costs, and decisions. ARBR gives your applications one control layer across your AI stack. Connect once through an OpenAI-compatible endpoint to route, govern, observe, evaluate, and deploy across AI models. Open source, MIT-licensed, provider-neutral, and self-hosted.
Products used by ARBR
Explore the tech stack and tools that power ARBR. See what products ARBR uses for development, design, marketing, analytics, and more.
Engineering & Development 3
Engineering & Development 3
liteLLMOne library to standardize all LLM APIs
5.0 (24 reviews)
We chose LiteLLM for its unified interface across model providers and open-source flexibility. It reduces the need to maintain separate provider integrations, letting us focus on ARBR’s evaluation, governance, and human-approved model changes. Its OpenAI-compatible interface also makes it a practical fit for teams that want to add ARBR without replacing their existing gateway.
GitHubHow people build software
5.0 (669 reviews)
We chose GitHub because ARBR is open source, and we wanted developers to easily explore the code, report issues, and contribute improvements. Having the repository, issue tracking, and pull requests in one place keeps collaboration simple. GitHub’s established open-source community made it a natural fit for building ARBR in the open.
Claude CodeAnthropic’s deep-context AI coder
5.0 (660 reviews)
We chose Claude Code because it fits directly into our development workflow. Working within the codebase helps us explore implementation options, debug issues, and iterate on ARBR without repeatedly explaining the project’s context. The appeal was practical collaboration on engineering tasks, while keeping architectural decisions and final code review with our team.
General 1
General 1
Docker for Beginnersdocker for beginners
5.0 (4 reviews)
We chose Docker to make ARBR easier to run and self-host. Packaging the application and its dependencies together reduces manual setup and helps keep environments consistent. For an open-source project, that means developers can spend less time troubleshooting installation and more time exploring the product. Its familiar workflow made it a practical fit for our team and contributors.