[Canonical HTML page](https://githits.com/why-githits/)

Why GitHits

# Why the code context layer matters

Coding agents can inspect the code in your repository. But application behavior also comes from open-source frameworks, SDKs, libraries, and packages outside that repository.

GitHits is the code context layer for AI coding agents. It gives them tools to navigate dependency source, read documentation, inspect package metadata and dependency graphs, check vulnerabilities, review changelogs, compare upgrades, and find prior art.

The tools answer different questions. When the agent needs to understand an API, it can search for a symbol or read the source. When it is evaluating a package, it can inspect its dependencies, license, and known vulnerabilities. When it is planning an upgrade, it can review what changed between releases. When it needs an implementation pattern, it can look at how open-source projects solved similar problems.

GitHits also keeps the version straight. When the agent specifies a package version or repository ref, GitHits searches the code and documentation for that target.

The agent keeps working in the same coding tool and keeps its view of your local repository. GitHits adds visibility into the open-source dependencies behind it. Together, they let the agent inspect the code it is changing and the code that change relies on.

Without GitHits

### The agent sees your repository, but not the open-source code behind it.

The agent can inspect your application code. Dependency source, documentation, package data, vulnerabilities, and release history remain outside its view, so it has to search elsewhere or guess.

30% — local repository visible

With GitHits

### The agent can inspect the whole open-source code stack.

GitHits adds tools for dependency source, documentation, package data, vulnerabilities, changes, dependency graphs, upgrades, and prior art.

100% — local repository + open-source dependencies visible

## What developers say

> GitHits has built a version-aware code example engine that allows AI coding agents and developers to inspect real implementations, navigate dependency source code, analyze package information, and retrieve repository context.

Jesse Landry · Senior Consultant at Vention · Founder & CEO of DevCuration · Source: [Blog](https://devcuration.com/articles/githits-raises-175m-pre-seed-to-give-ai-coding-agents-something-they-desperately-need-context)

> The MCP is great! Whenever I don't like a solution, or my agent is stuck, I say use GitHits and it synthesizes a better solution based on real projects. I've had good results with frontend (html, css) and Golang, too.

Peter Warnock · Full-Stack Developer & Technical Leader · Source: [Hacker News](https://news.ycombinator.com/item?id=46105112)

> GitHits changed my workflow because it's not a search engine, it's a discovery engine. A search engine is for when you already know what you're looking for. But a discovery engine helps you find solutions you didn't even know existed.

Atharv Singh · SDE · Source: [Blog](https://githits.hashnode.dev/how-githits-changed-the-way-i-code-a-deep-dive-into-its-architecture)

Keep exploring

* [The Solution](/the-solution.md)
* [The Builders](/the-builders.md)