FalkorDB
Solutions
Use cases
Why FalkorDB
Developers
Auryn for developers

Your Agent, With a Map of Your Code.

Auryn plugs into the coding agent you already use. You ask in plain language; your agent answers from a graph of your whole codebase instead of reading its way through files.

You

ask a question in plain language

“how does checkout flow?”
Your agent

decides what to look up

trace_entrypoint(…)
Auryn

follows the real connections

CALLS · CALLS_API
FalkorDB

holds the graph, on your machine

~5 ms lookups
Your repos

one or many, every language

TS · C# · Python · SQL

Ask your agent. It walks the graph.

A real session on Meridian, a sample storefront made of four repositories: a TypeScript web portal, a C# API gateway, a Python platform core and a SQL database. Nothing to configure and nothing indexed upfront: the agent builds the graph on the first question and keeps using it.

~/meridian — claude web-portalTS api-gatewayC# platform-corePython platform-dbSQL

One install. Then just ask.

Auryn connects itself to the coding agent you already use and keeps its graph on your machine. Nothing to configure, nothing added to your repository.

Restart your agent and ask your first question. A shared database for your team, a scripted install, or any other agent: see Docs → Connect your agent.

Terminal
$ pip install falkordb-auryn $ auryn install
1 · Install The CLI, with an embedded FalkorDB
2 · Connect Registers with your agent
3 · Ask The graph builds on the first question

What the agent gets.

A small set of read-only tools, each answering one kind of question about your code.

Where is it, and what calls it?

who_calls("billing.charge") → 3 callers, 2 repos

locate who_calls callees

How does A reach B?

find_path(SubmitOrderButton, ORDER_LINES) → 3 hops

find_path

What breaks if I change this?

impact_of_diff(HEAD~1) → 2 callers, 1 job, 1 screen

impact_of impact_of_diff

What does this endpoint do, end to end?

trace_entrypoint("POST /api/orders") → browser to table

trace_entrypoint

Plus search by meaning, raw read-only Cypher and the tools that build the graph. The full list: Docs → Agent tools.

Fifteen languages, auto-detected.

Every language gets a fast structural pass. Python and C# also get a full semantic analysis, so calls land on the code that actually runs. Install only what you need with extras, e.g. "falkordb-auryn[python,csharp]".

Python Semantic
C# Semantic
TypeScript · JS Structural
Java Structural
C Structural
C++ Structural
Go Structural
Rust Structural
PHP Structural
Julia Structural
Ruby Structural
Kotlin Structural
Swift Structural
Bash Structural
PL/SQL Structural
Structural · fast pass: symbols, calls, imports Semantic · plus a full analysis in the background

Live SQL schema

Tables, columns, keys, indexes and views from PostgreSQL, MySQL, SQLite and more.

Live Oracle

Packages, procedures, functions and triggers, read straight from the database.

One vocabulary, every language.

Every ingestor writes the same kinds of nodes and relationships, so one query follows a request from the browser, through the API, to the table it writes, regardless of the language at each layer.

One checkout, from the browser to the database
Function placeOrder web · TS
CALLS_API
APIEndpoint POST /api/orders http
EXPOSES_ENDPOINT
Method OrdersController.PlaceOrder api · C#
DISPATCHES_TO
Procedure PKG_ORDERS.SUBMIT db · PL/SQL
WRITES · INSERT
Table ORDER_LINES db · Oracle
Relationships, by what they answer
Who calls what
CALLS CALLS_API DISPATCHES_TO
How types relate
EXTENDS IMPLEMENTS DEPENDS_ON
What touches data
READS WRITES REFERENCES
How it’s exposed
EXPOSES_ENDPOINT ACCEPTS RETURNS
Where it lives
HAS_* DEFINED_IN

Every node and edge, per language: Docs → Graph model.

Try it on your own repo.

One command, about five minutes, entirely on your machine.