ProtoMap
Section titled “ProtoMap”ProtoMap by HoundDog.ai maps your gRPC services: which services call which, through which methods and protobuf fields, down to every call site. Run it on your own infrastructure, explore your architecture in its platform, ask its assistant what a change would break, and give the same graph to coding agents such as Claude Code.
What You Can Do
Section titled “What You Can Do”- See your architecture. Every gRPC service defined across your repositories, in monorepos or across microservices, and how they connect, by repository, service, method, message, and field.
- Assess the blast radius of a change. Before you change a service, method, or field, see the services, callers, and call sites it affects.
- Find every call site of an RPC. Which services call a method, in which file and function, and the call itself.
- Trace how a field flows. Follow a protobuf field through the code step by step, with the code at each step, from one service into the next.
- Ask the assistant. It answers from your scans, with file locations, and draws diagrams, using the AI provider you connect.
- Give coding agents the graph. Over MCP, with your uncommitted changes laid over the shared graph.
How It Fits Together
Section titled “How It Fits Together”- Install ProtoMap Server in your environment with Docker Compose.
- Scan your repositories with the CLI. Scans run on your computers or in your CI pipelines, and upload to your server.
- Explore the graph. Scans of each repository’s primary branch join the shared graph that everyone in your organization sees, in the workspace and through the assistant.
- Connect your coding agents. They read the same graph, with your own changes laid over it as you edit.
ProtoMap reads .proto files and the gRPC code that serves and calls them in Go, C#, Java, Kotlin, Python, Rust, Swift,
TypeScript, and JavaScript. See Supported Languages.
Does ProtoMap need to build or run my code?
Section titled “Does ProtoMap need to build or run my code?”No. The CLI analyzes your source files directly, with no build and no compiler. It reads the .proto files in the
repository, so the code generated from them does not need to be checked in.
Where does my code go?
Section titled “Where does my code go?”Scans run on your own computers or CI runners. Each scan uploads a description of your gRPC code to your ProtoMap Server, including short code snippets at the locations it records, so the platform can show them. Nothing else is uploaded, and no repository host integration is needed. When you chat, the assistant sends your questions and the graph data needed to answer them to the AI provider your organization connects.
Does ProtoMap use AI to find services and calls?
Section titled “Does ProtoMap use AI to find services and calls?”No. A deterministic static analysis finds every service, call site, and flow: the same files always give the same results. AI is optional, and used on top of those results: the assistant answers questions about them, and a graph review judges how likely each uncertain flow is to be real.
What if ProtoMap cannot tell for sure?
Section titled “What if ProtoMap cannot tell for sure?”ProtoMap favors recall: it keeps a flow it cannot rule out, and marks it uncertain, rather than drop it. For example, a call whose method name is built from a string links uncertainly to every method it could be. See Terms and Concepts.
Contact
Section titled “Contact”If you need help or would like to send feedback, create a GitHub issue or email us at [email protected].