A live service catalog and API context layer, generated from your code

Deterministic static analysis builds a continuously fresh inventory of every service, API, field, and downstream consumer. Centralized across your org, or local on a single repo. Used by platform engineers, technical PMs, and AI coding agents.

ProtoMap By HoundDog.ai
New chat UserService one hop out ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
What calls UserService, and what does it call?
Thinking…
2 graph queries, 1 workspace view
UserService has 479 callers and 3 callees, one hop out:
It lives in protomap-test-golang, with 6 methods.Most callers use GetUser.It calls AuthService, SessionService, and EmailService.
Shown in the workspace Service UserService
What calls UserService, and what does it call? Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Callers Service AccountService Service BillingService Service CheckoutService Service ReviewService 1–4 of 479 total
479
Repository protomap-test-golang Service UserService Method GetUser
3
Callees Service AuthService Service SessionService Service EmailService
Service acme.users.v1.UserService Methods
MethodRequestCallers
Method GetUser Message GetUserRequest 412
Method UpdateUser Message UpdateUserRequest 61
Method ListUsers Message ListUsersRequest 24
Refreshed on every pull request Same input, same output

No one in your org has an accurate picture of your services

The teams that need that picture most are improvising.

API specs do not describe consumers

OpenAPI, protobuf, and GraphQL schemas tell you what an API is. They do not tell you which services call it, which fields are touched, or what fails when you change it.

Technical PMs maintain catalogs in spreadsheets

The spreadsheet goes stale the moment a PR merges, and the next planning cycle starts from guesswork.

Cross-repo change impact is tribal knowledge

“Who calls this?” gets asked in Slack and answered with a half-remembered service name. The real answer lives across millions of lines and dozens of repos, with no one source of truth.

A service catalog, generated and refreshed by CI

The catalog is built by ProtoMap, a deterministic static analyzer that reads your code on every pull request, with no manual data entry.

01

Services & owners

Every service in every repo, with language, protocol, and maintainers drawn from git history.

02

APIs & fields

Every service, RPC, message, and field, extracted from protobuf files and the code that serves and calls them.

03

Consumers & call sites

For every API, the exact list of services that call it and the line numbers where they call it. No grepping.

04

Cross-repo dependency graph

A directed graph of service-to-service relationships, queryable through the assistant, MCP, or a visual viewer.

ProtoMap By HoundDog.ai
New chat Services and maintainers ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
List all gRPC services and who maintains them
Thinking…
1 graph query, 1 workspace view
715 services across 38 repositories. The largest:
UserService: Dana Kim, 479 callers.AuthService: Priya Shah, 1,000 callers.CheckoutService: Marco Ruiz, 12 callers.
Shown in the workspace Service 715 services
List all gRPC services and who maintains them Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Service 715 services
ServiceMethodsCallersCallees
Service AuthService 6 1,000 2
Service UserService 14 479 5
Service CheckoutService 1 12 6
ProtoMap By HoundDog.ai
New chat product_id blast radius ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
What is the blast radius of changing product_id?
Thinking…
2 graph queries, 1 workspace view
CartItem.product_id reaches 2 sender and 4 receiver services in 1 repository:
Sent by CartService and CheckoutService.Received by those two, EmailService, and ShippingService.Defined in demo.proto:30, and 4 more copies.
Shown in the workspace Field product_id
What is the blast radius of changing product_id? Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Sent from Service CheckoutService Service CartService
2
Message CartItem Field product_id
4
Received by Service ShippingService Service CartService Service CheckoutService Service EmailService
Field hipstershop.CartItem.product_id
PropertyValue
Type string
Definition microservices-demo › demo.proto:30
Blast radius 2 senders · 4 receivers · 1 repository
ProtoMap By HoundDog.ai
New chat CoverShift callers ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
Who calls CoverShift, and from where?
Thinking…
2 graph queries, 1 workspace view
42 methods call CoverShift, all from the facilities services. The first call sites:
FindIncident in building_incident_lookup.go:59SelectResources in emergency_resource_selection.go:59Respond in facility_emergency_coordination.go:73
Shown in the workspace Method CoverShift
Who calls CoverShift, and from where? Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Callers Method FindIncident Method SelectResources Method AssessEvacuation Method Respond 1–4 of 42 total
42
Service ShiftCoverageCoordination Method CoverShift
2
Callees Method Authenticate Method EnrollLearner 2 total
Method fixture.workforce.v1.ShiftCoverageCoordination/CoverShift Call sites
FromLocation
Method BuildingIncidentLookup/FindIncident building_incident_lookup.go:59
Method EmergencyResourceSelection/SelectResources emergency_resource_selection.go:59
Method FacilityEmergencyCoordination/Respond facility_emergency_coordination.go:73
ProtoMap By HoundDog.ai
New chat UserService one hop out ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
What calls UserService, and what does it call?
Thinking…
2 graph queries, 1 workspace view
UserService has 479 callers and 3 callees, one hop out:
It lives in protomap-test-golang, with 6 methods.Most callers use GetUser.It calls AuthService, SessionService, and EmailService.
Shown in the workspace Service UserService
What calls UserService, and what does it call? Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Callers Service AccountService Service BillingService Service CheckoutService Service ReviewService 1–4 of 479 total
479
Repository protomap-test-golang Service UserService Method GetUser
3
Callees Service AuthService Service SessionService Service EmailService
Service acme.users.v1.UserService Methods
MethodRequestCallers
Method GetUser Message GetUserRequest 412
Method UpdateUser Message UpdateUserRequest 61
Method ListUsers Message ListUsersRequest 24

Deprecating street_address on the shared Address message

Here’s an example based on the Google Cloud Online Boutique microservices demo (eleven polyglot microservices, gRPC over protobuf). The protobuf change is one line. The blast radius is what matters.

ProtoMap By HoundDog.ai
New chat street_address blast radius ···
Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?
Who sends and receives street_address?
Thinking…
2 graph queries, 1 workspace view
Address.street_address reaches 2 senders and 3 receivers:
The frontend and CheckoutService send it.ShippingService, EmailService, and CheckoutService receive it.It is personal data: check each receiver before renaming it.
Shown in the workspace Field street_address
Who sends and receives street_address? Ask about your code and data…
Opus 5.5 · High
20 services
ServiceMethodsCallers
Service AuthService 4 1,000
Service CartService 3 2
Sent from Service frontend Service CheckoutService
2
Message Address Field street_address
3
Received by Service ShippingService Service EmailService Service CheckoutService
Field hipstershop.Address.street_address
PropertyValue
Type string
Definition microservices-demo › demo.proto:142
Blast radius 2 senders · 3 receivers · 1 repository

One sender service, three receiver services, one repository. Each one needs a PR before street_address can be safely removed.

Refreshed on every pull request

The catalog is regenerated from source on each PR, not on a schedule and not by hand. Nothing drifts.

  1. 1

    CI hook on every PR

    A GitHub, GitLab, or Bitbucket integration runs ProtoMap against the diff and the working tree.

  2. 2

    Deterministic Rust analyzer

    Parses gRPC today, with GraphQL and REST coming soon. Source languages: Python, JavaScript, TypeScript, C#, Go, Java, Swift, Rust, and Kotlin.

  3. 3

    Catalog and MCP surface update

    The catalog refreshes in place. AI agents and humans query the same source of truth through the assistant, MCP, or a web viewer.

No embeddings. No probabilistic recall. The analyzer is deterministic by design: two runs of the same commit produce identical catalogs.

For humans first. Agents too.

The catalog earns its keep before you ever turn on an AI coding agent. Three readers, one source of truth.

Platform & staff engineers

Pull request review, migration planning, deprecation hygiene, on-call investigations.

PR reviewMigrationsDeprecationsOn-call

Technical product managers

Org-wide service inventory, ownership clarity, what we ship to which customer segment. Replace the spreadsheet you keep apologizing for.

InventoryOwnershipRoadmapCustomer mapping

AI coding agents

Claude Code, Cursor, Codex, and Copilot read the same catalog through a local MCP server. The catalog is what lets them reason about cross-repo change without grep-bombing.

MCPCLI

Building this for your AI coding agents? See AI Coding Agent Context

faster per prompt
7.7×
cheaper per prompt
6.4×
fewer tokens
13×

Claude Code with Opus 5.5 at high effort, across 20 prompts on 9 gRPC repositories (5M LOC), with higher accuracy (100% vs. 98%). See the benchmarks

Watch ProtoMap answer the questions agents get stuck on.

HoundDog.ai ProtoMap live demo at MozFest 2026 10:53 Live demo · MozFest 2026

HoundDog.ai ProtoMap Demo at MozFest

Live demo of HoundDog.ai’s ProtoMap at MozFest’s Open Source House: callers and callees, and the blast radius of changing a field name.

HoundDog.ai Benchmarks · Side by side ProtoMap × Claude Code 7× faster · 36× cheaper Claude Code alone6:01 · $14.44 Claude Code + ProtoMap0:50 · $0.40 1:09 Benchmarks · Video

ProtoMap × Claude Code, side by side

The same prompt in two live sessions: ProtoMap’s answers in 50 seconds for $0.40, the baseline’s in 6 minutes for $14.44.

Start free on one machine. Roll out to your organization.

Step 1 · Free

Install it on your machine

Install the self-hosted platform and CLI with Docker, scan your repositories, and query ProtoMap in plain English or over MCP. Free for code scanned on your machine.

  • Self-hosted platform and CLI scanner
  • Bring your own AI provider: Anthropic, OpenAI, Google and others
  • MCP server for your coding agent, including uncommitted changes
Terminal
git clone https://github.com/hounddogai/protomap.git
cd protomap
./self-hosted/scripts/install.sh
Step 2 · Enterprise

Organization-wide context

Enterprise keeps context current across every repository in your organization, so agents no longer clone repositories they don’t own.

  • Cloud hosted or deployed on-premises in your org
  • Direct integrations with GitHub, Bitbucket, and GitLab
  • Runs scans in CI on every pull request
  • Every agent gets context for every repository over MCP

Why not just build another AI agent?

AI agents are great at reasoning. They are an expensive and inefficient way to repeatedly rediscover deterministic facts about your codebase.

Without precomputed context, every agent has to search files, follow references, inspect protobuf definitions, and reconstruct dependencies before it can start on the actual problem. Across developers, prompts, and repositories, you pay for the same discovery again and again in tokens, latency, and compute.

HoundDog.ai separates discovery from reasoning. ProtoMap computes API, field, consumer, and service relationships deterministically, keeps them current as code changes, and makes that evidence available to your existing AI agents through MCP.

  1. 1Static analysis discovers.
  2. 2AI reasons.
  3. 3MCP delivers.

Compute the facts once. Keep them fresh. Let every authorized AI agent reason over them.

Frequently asked questions

What is in the service catalog?

Every service, API, field, and downstream consumer across your repos. Service owners, language and protocol, call sites, and cross-repo dependency edges are captured deterministically from the code.

How is the catalog kept fresh?

A CI hook runs ProtoMap on every pull request. The catalog updates the moment code lands. There is no manual edit step, no spreadsheet to maintain, and no nightly batch that drifts behind the codebase.

How is this different from Backstage?

Backstage is a developer portal. Its software catalog is built from catalog-info.yaml files that teams write and keep next to their code. Backstage can discover and register those files across your repositories automatically, but the contents are written by hand: which APIs a service provides and consumes, and what it depends on, are declared in YAML rather than extracted from the code. ProtoMap generates the catalog from the code itself, so the inventory and dependency map are accurate by construction rather than by discipline.

Does my code leave my machine?

No. Analysis runs locally or inside your CI environment. Source code never leaves your infrastructure.

Which API protocols are supported?

gRPC is supported today, with GraphQL and REST coming soon.

Try it on your code.

Install the self-hosted version for free. It runs on your machine with Docker, and your source code stays in your environment.

Paste into your coding agent

Set up ProtoMap and show me what it can do. ProtoMap maps gRPC services and protobuf messages across repositories, and gives coding agents that graph over MCP. Docs: https://docs.protomap.ai/quickstart/

Tell me what you are about to do before each step that installs something.

1. Check that this computer has git, Docker with Compose 2.23.1 or newer, at least 4 GB of RAM, and 20 GB of disk space. If anything is missing, tell me and stop.

2. Install ProtoMap Server, in a folder outside this repository:

   git clone https://github.com/hounddogai/protomap.git
   cd protomap
   ./self-hosted/scripts/install.sh

   The installer asks questions. Choose Trial, which runs PostgreSQL locally and logs the CLI in, and keep the default port.

3. Show me the address and the one-time setup key the installer prints. Ask me to open the address, enter the key, and create my organization and owner account. Wait until I say that's done.

4. Scan this repository, from a new shell so the CLI is on the PATH:

   protomap scan .

   If it has no gRPC services in a supported language, tell me, and offer to scan a public example instead:

   git clone https://github.com/GoogleCloudPlatform/microservices-demo.git
   protomap scan microservices-demo

5. From the scanned repository's folder, add ProtoMap to yourself as an MCP server:

   Claude Code: claude mcp add protomap -- protomap mcp serve
   Codex: codex mcp add protomap -- protomap mcp serve
   Antigravity: add "protomap": { "command": "protomap", "args": ["mcp", "serve"] } under mcpServers in ~/.gemini/config/mcp_config.json
   Others: https://docs.protomap.ai/coding-agents/

   Tell me if I need to restart you for it to take effect.

6. Tell me what the scan found, then use ProtoMap's tools to answer one question about my services, such as which services call a method and where. Suggest two more questions I could ask.