The world's code has a genome.

Sequencing every public open source repo into a compiler-accurate Lossless Semantic Tree — so the code the world runs on can be understood and improved, at scale.

What is the Code Genome Project

The world's code has a genome, and this is where it's sequenced, stored, and navigable.

Enterprise software consists of up to 90% third-party and open source components, stitched together in different ways for business functionality. This software is the basis of the Code Genome Project. The goal: understand codebases broadly, across open source and enterprise, and share deterministic recipes that advance them. It's all open to developers and their agents alike through code search and a remote MCP server.

Put the OSS Code Genome to work

Searching

Explore the sequenced code of thousands of open source repositories. Search by type, symbol, and call site, not just strings, and surface any API or pattern in milliseconds. Powered by Moderne's Trigrep search.

Search the corpus →

Surfacing to AI

A remote MCP server opens the full Code Genome to coding agents. They can find any method or type, see how it's really used, and compare versions, all resolved through the type system, not text. Connect in one click to power up your agents.

Connect your agent →

Foundation of the Code Genome Project

Sequencing

Each open source repository is compiled into a Lossless Semantic Tree. Compiler-accurate, lossless, polyglot^*. One tree per repository, lined up side by side, so the entire open source ecosystem reads as a single corpus. It's the substrate everything else is built on.

Splicing

OpenRewrite recipes rewrite the genome: 10,000+ deterministic programs. Migrate a framework, fix a CVE, or enforce a standard, the same way every time. Recipes live in the project, ready for developers and their agents to use, adapt, and extend.

Browse recipes →

^* Today the Code Genome Project sequences the Java ecosystem; it's expanding to the full breadth of languages the LST supports, including Python, C#, JavaScript/TypeScript, Scala, and more.

First result in 21 ms

Recipe catalog

Every OpenRewrite and Moderne recipe, with the artifact you add to get it and its license. Add the artifact to your build to run it — the Maven repository serves them, free for open source.

All of open source at your agent's fingertips.

A remote MCP server over the entire Code Genome corpus, growing to encompass all the world's provably used open source. Your agent navigates and reads all of open source as if it were fully resolved in an IDE it could click around. Try any tool below, then connect it in one line.

Connect your agent

claude mcp add --transport http codegenome https://api.codegenomeproject.org/mcp

Or one click: Add to Cursor Add to VS Code

Remote MCP over Streamable HTTP at https://api.codegenomeproject.org/mcp. Windsurf, Cline, and Zed take the same URL; stdio-only clients bridge with npx mcp-remote https://api.codegenomeproject.org/mcp.

The MCP tools

The exact tools your agent gets, with the exact descriptions it reads — run any of them against the public corpus and read the JSON that comes back. The find_* and usage_examples tools resolve through the corpus's type tables, so they catch what a grep or a docs pipe can't.

Artifacts

A read-only, Maven-compatible repository serving the OpenRewrite OSS recipes, Moderne's licensed recipe modules, and the Moderne CLI — free for open source. Point your build at it and resolve any recipe artifact straight from the catalog.

Add the repository

artifacts.codegenomeproject.org/maven

Declare the Code Genome repository, then add any recipe module as a dependency — versions come from the catalog.

<repository>
  <id>codegenome</id>
  <url>https://artifacts.codegenomeproject.org/maven</url>
</repository>

Install the CLI

The Moderne CLI runs recipes locally and installs any recipe artifact on demand.

mod config recipes jar install org.openrewrite.recipe:rewrite-migrate-java:LATEST

Free for open source. Apache-licensed recipes run anywhere; MSAL and proprietary modules require a Moderne license.

Install the CLI

The Moderne CLI (mod) runs OpenRewrite recipes and compiler-accurate code search on your machine or in CI — against your own repositories or the public Code Genome corpus. One command to install; nothing to sign in for.

curl https://api.app.moderne.io/cli | bash

No token or sign-in required. Downloading and installing the CLI is completely unauthenticated. Repository tokens are only for pulling licensed artifacts from the artifact repository — a separate flow you don't need to get started.

Inspect the script first

Piping a script straight into your shell? Read it first. The installer lives at a stable URL you can open in a browser or curl on its own before running it:

https://api.app.moderne.io/cli

Open api.app.moderne.io/cli to review exactly what runs. The script detects your OS and architecture, downloads the matching mod binary, and puts it on your PATH — no privileges beyond your own shell.

Direct downloads

Prefer to grab a specific build — for a CI image, an air-gapped install, or pinning a version? Every platform binary is published, unauthenticated, to the public artifact repository. Browse them at artifacts.codegenomeproject.org/maven/io/moderne/.

Platform	Architecture	Artifact
macOS	Apple Silicon & Intel	moderne-cli-osx
Linux	x86-64	moderne-cli-linux-x64
Linux	ARM64 · aarch64	moderne-cli-linux-aarch64
Windows	x86-64	moderne-cli-windows
Any (JVM)	Requires Java 17+	moderne-cli .jar

The one-line installer above resolves the right one automatically — this table is for when you want to pick it yourself.

Where it's published & what it uses

Published to Maven Central and Cogenom

The CLI and the Moderne connector are published to both Maven Central (io.moderne:moderne-cli) and the Cogenom artifact repository (artifacts.codegenomeproject.org/maven) — so builds and CI can resolve them from wherever they already pull dependencies, with no new registry to wire up.

Default recipe source

Out of the box, the CLI resolves recipes from Maven Central — the open source catalog runs with zero configuration.

Add the licensed recipe repository

Licensed (MSAL & proprietary) recipes live in the token-gated artifact repository. Point mod at it with your repository token — this is the only step that needs credentials:

mod config recipes artifacts maven add https://artifacts.codegenomeproject.org/maven --user=<email> --password=<token>

Don't hand-fill this. Sign in to the setup page to copy the command with your email and token already in place, alongside the matching Maven, Gradle, and MCP configs.

Per-tenant install script

The install script can be customized per tenant — enterprise customers get a tenant-specific installer that pre-configures the connector and the repository their CLI should use, so curl … | bash lands fully set up.

Verify the install

Confirm the CLI is on your PATH and print its version:

mod --version