Pay 3x less for Claude to understand your code

No. Pharaoh stores structural metadata only: function names and signatures, file paths, import/export relationships, call edges, complexity scores. No source code, no function bodies, no environment variable values. Signatures, doc comments, routes and constant values are encrypted per account, and the clone used for mapping is deleted when each run ends. The parser is open source, so you can audit exactly what gets extracted.

Under 5 minutes. Install the GitHub App, select repos, add the MCP endpoint to your AI tool. Pharaoh parses the codebase automatically. A 50K LOC TypeScript project maps in about 60 seconds.

A GitHub webhook re-maps your live repos on every push to the default branch, so the graph stays within one commit of HEAD. Your AI tool can also refresh a repo on demand.

TypeScript and Python today, with full support for imports, exports, call chains, decorators, and barrel files. More languages coming — the parser is built on tree-sitter, which supports 100+ grammars.

Sourcegraph answers "where is this code?" Pharaoh answers "what breaks if I change it?" Sourcegraph is search and navigation. Pharaoh is blast radius, dependency chains, and the endpoints and jobs a change reaches. Different tools, different questions.

CodeScene analyzes file-level health using git history: complexity trends, code age, developer coupling. Pharaoh analyzes cross-module architecture using a knowledge graph: how modules connect, what depends on what, which endpoints and jobs a function feeds. CodeScene is behavioral. Pharaoh is structural.

SonarQube does line-level static analysis: bugs, code smells, security issues. Pharaoh does system-level structural analysis: blast radius, dependency chains, module boundaries. SonarQube looks at lines. Pharaoh looks at architecture.

Yes, on Pro, where every repo is live. Your AI searches across all of them, so it finds the function that already exists in another service before writing a new one. No monorepo required. Everyone on the team connects to the same MCP endpoint.

Yes. Pharaoh reads repository contents to map them and can't write to your code. All graph data is tenant-isolated.

Your workspace goes back to the free plan. One repo stays live; the others stop answering, and their graphs are deleted after 30 days. Re-subscribe within 30 days and they come straight back. No lock-in: Pharaoh reads your code, it doesn't store it.

That's exactly who Pharaoh is for. Claude Code and Cursor are powerful, but they read files one at a time with no structural awareness. They don't know what depends on what, which endpoints a function feeds, or whether the code they're about to write already exists somewhere else. Pharaoh gives them that context via MCP. Same tools, smarter decisions.

One prevented regression pays for months of Pharaoh. Without architectural context, AI tools introduce duplicate utilities, break downstream callers they can't see, and create exports that never get wired to entry points. Each of those costs hours of debugging. Pharaoh fixes the root cause — the AI's blind spot — for less than a single production incident.

Trust shouldn't depend on team size. It should depend on architecture. Pharaoh never stores source code. Only structural metadata like function names and dependency edges. Pharaoh can't write to your code. Tokens are encrypted with per-tenant keys. The parser is open source for full auditability. And if you uninstall the app, your graphs are deleted within 30 days, and there's nothing to leak because there's no code to leak.