Auryn

Auryn turns your codebases into one codegraph in FalkorDB. Your coding agent queries it over MCP and traces calls across repos and languages, with file and line

What is Auryn?

Auryn turns your codebases into one codegraph in FalkorDB. Your coding agent queries it over MCP and traces calls across repos and languages, with file and line citations. 16 languages, runs locally, no server needed to start.

Overview of Auryn

What it is

Auryn is an open-source tool that turns codebases into a queryable codegraph stored in FalkorDB. It parses source code to build a graph of functions, types, tables, endpoints, and the edges between them (such as CALLS, EXTENDS, READS/WRITES, DEPENDS_ON). Coding agents can then query this graph over the Model Context Protocol (MCP) to trace calls across repositories and languages, with file and line citations. It supports 16 languages plus SQL, runs locally, and requires no server to start.

Key features

  • Builds a codegraph of functions, types, tables, endpoints, and edges (CALLS, EXTENDS, READS/WRITES, DEPENDS_ON) from any codebase.
  • Provides MCP tools for agents, including locate, who_calls, callees, find_path, impact_of, trace_entrypoint, search_code, get_context, get_schema, and run_cypher.
  • Supports incremental resync: on a commit or branch switch, only changed files and affected code are re-parsed.
  • Offers two levels of analysis: a fast structural pass for all languages, and a deep semantic pass for Python (Jedi) and C# (Roslyn).
  • Enables cross-repo references: when code points to a symbol in another repository, Auryn records it and links it once that repo is ingested.
  • Uses a single vocabulary for every language, so a single query can follow a request across TypeScript, C#, and PL/SQL.
  • Parsing runs locally; the graph lives on your machine or on a FalkorDB server you run, with no hosted service or telemetry.

Use cases

  • Determining who calls a specific function and tracing callers multiple hops deep.
  • Assessing the blast radius of a signature change across CALLS, DEPENDS_ON, READS, and WRITES edges.
  • Finding the shortest path between two symbols, such as whether an endpoint touches a particular table.
  • Tracing how a request flows from a UI component through an API to a database, across multiple languages.
  • Answering structural questions about a codebase with file and line citations, instead of grepping or reading files manually.

Getting started

Two commands, zero infrastructure: bash pip install falkordb-auryn auryn quickstart This boots FalkorDB embedded (in-process, no daemon), ingests a small payments API that ships inside the package, and opens the viewer. For your own project: bash auryn quickstart path/to/your/repo Requirements: Python ≥ 3.12. The in-process database is fetched automatically on first auryn quickstart on macOS and Linux (recent glibc). On native Windows or older-glibc Linux, point at a remote FalkorDB with auryn install --backend remote. Add live-DB drivers with falkordb-auryn[all]. For an isolated tool install: uv tool install falkordb-auryn[embedded]. From a clone: uv sync, then uv run auryn quickstart.

License and pricing

The license is MIT. The pricing type is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/falkordbauryn.svg)](https://yunodb.com/tools/falkordbauryn?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/falkordbauryn?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/falkordbauryn.svg" alt="Featured on YunoDB" height="20"></a>