GitHits beta 0.9
Give your AI coding agent access to open-source code
296 followers
Give your AI coding agent access to open-source code
296 followers
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Interactive
Free
Launch Team / Built With
GitHits beta 0.9
We are often asked how GitHits compares to Context7, so here is the comparison:
GitHits and Context7 are both available as MCP servers and CLIs that provide external context to AI coding agents. Both help fill gaps in model knowledge by retrieving information about libraries and dependencies.
Context7 is centered on version-aware library documentation.
GitHits also retrieves version-aware library documentation, while providing access to dependency source code, package metadata, and implementation examples from open-source repositories.
Capability
GitHits
Context7
Version-aware documentation
✅
✅
Open-source implementation examples
✅
❌
Version-aware source code search & navigation
✅
❌
Version-aware package metadata
✅
❌
MCP server
✅
✅
CLI
✅
✅
Documentation
Both tools retrieve documentation for specific library versions, allowing agents to work with current APIs instead of relying solely on model knowledge.
Context7
Context7's workflow consists of resolving a library and retrieving documentation for it. The results contain relevant documentation sections together with code snippets and explanatory text from the indexed documentation.
Tools
GitHits
GitHits provides version-aware documentation together with source code, package metadata, and implementation examples. Agents can search documentation, browse available pages, and read individual documentation pages for a specific package version.
Tools
The same search command can also search source code or symbols by changing the --source option.
Implementation Examples
Both products return code, but the source of that code is different.
Context7
Context7 returns code snippets from indexed documentation. These snippets accompany the relevant documentation and illustrate how an API is intended to be used.
Tools
GitHits
GitHits retrieves implementation examples from open-source repositories. Rather than extracting snippets from documentation, it searches real projects for implementations matching a natural-language query and links back to the original source.
Tools
Documentation snippets help explain an API. Implementation examples show how similar problems are solved in real applications.
Source Code
Context7
Context7's interface is centered on documentation retrieval. Agents resolve libraries and retrieve documentation, including code snippets and explanatory text from the indexed documentation.
GitHits
AI coding agents already use search, file listing, file reads, and grep to understand your local codebase. GitHits extends those same capabilities to dependency source code, allowing agents to inspect implementations without cloning repositories or leaving their existing workflow.
Tools
These tools allow agents to search indexed code and symbols, inspect repository structure, read source files, and perform deterministic grep across dependency source code.
Package Metadata
Context7
Context7 retrieves library documentation. Its public interface is centered on documentation rather than package inspection.
GitHits
GitHits provides package inspection commands for dependency analysis and upgrade planning.
Tools
These commands allow agents to inspect package metadata, dependency graphs, known vulnerabilities, changelogs, release notes, and factual upgrade information for specific package versions.
Overall
GitHits and Context7 both help coding agents retrieve information that is not reliably available from model knowledge alone.
Context7 is centered on version-aware library documentation. The workflow is straightforward: resolve a library, then retrieve the relevant documentation.
GitHits also retrieves version-aware documentation, but exposes several retrieval primitives instead of a single workflow. This allows agents to adapt their retrieval strategy to the question they are trying to answer.
For example, if an agent needs to answer "Why does Express strip this header?", it might search the documentation first, then inspect the Express source code to trace the implementation. If the behavior changed between releases, it can also review the package changelog.
The products overlap in documentation retrieval but differ in the range of information they make available to an agent. Depending on the task, they can also complement each other.
Works great, I've been using Githits to explore implementation details from different libraries to ground my coding agent with real world examples. It's cool to point your coding agent towards an open source reference implementation that you know has already implemented what you want to implement.
GitHits beta 0.9
Thanks,@matti_ryttylainen Appreciate your kind words and all feedback you've provided along the way!
Giving a coding agent access to real open-source code is a smart idea. How does GitHits pick which repos or snippets are most relevant?
GitHits beta 0.9
@doganakbulut For snippets it's actually pretty involved. We run our own code index, so on top of standard ranking like BM25 we can use a bunch of code-specific signals for scoring. We also keep a separate document index for docs from canonical documentation sites. That lets us pull a balanced mix of function definitions, real usage examples, tests and related documentation, so the agent gets proper grounding, with each snippet linking back to the source it came from.
For picking which repos to pull from, right now we lean on a wide range of GitHub searches plus our own reranking. We're also building out a dedicated index for that part.
This app is seriously helpful and turns your coding agent in a top tier senior engineer. When I am introducing a new pattern or library in my code, I always think to find real battle tested implementations first from GitHits. Eventually you realize just letting a coding agent vibe out consequential and high leverage code is just plain dumb and irresponsible.
GitHits beta 0.9
Thanks,@lukeotwell! Let us know how we could make GitHits even better!
giving the agent access to open source code is the easy half. the hard half is helping it pick the right code. github has incredible code and also a long tail of broken half written experiments. how do you weight signals like maintained recently, used by many, tests pass, vs raw similarity to what the agent is trying to write?
Toolhouse
Congrats!
GitHits beta 0.9
Thanks@orliesaurus! Appreciate your support!
GitHits beta 0.9
Here's a press story worth checking out: Finnish Startup Raises €1.5M to Build the “Google for Code”
Selected quotes:
"Analysis of 16 widely used code-generating LLMs across 576,000 generated code samples found that 21.7% of the package names referenced in AI coding outputs were hallucinations — meaning no such packages existed in npm or PyPI. That’s nearly one in four dependencies simply invented by the model. GitHits is betting that plugging this specific gap — open-source code context for AI agents — is the infrastructure play that the entire coding-agent ecosystem has been missing."
"The origin story is refreshingly unglamorous."
"The GitHits Google for code framing isn’t just clever marketing — it’s a deliberate competitive positioning. As Heinisuo puts it: 'OpenAI, Anthropic, and Google have left a gap in the market. GitHits doesn’t compete with Codex, Claude Code, or Cursor, but complements them by bringing open-source code as context for agents to end retry loops and reduce token consumption.'"
"GitHits raised €1.5 million in a pre-seed round led by Vendep Capital, with participation from Trind VC and angel investors including Peter Sarlin, Zach Shelby, and Jerry Liu. That last name is notable — Jerry Liu is the co-founder of LlamaIndex, one of the most widely used frameworks for building LLM-powered applications. His backing signals more than capital; it signals conviction from someone who lives inside the AI agent stack daily."