Every GitHub profile leaves a trail. The challenge is knowing what that trail actually tells you.
Iām building RepoGhost, a project that investigates public GitHub accounts and repositories, surfaces useful evidence, and helps you ask questions about what it finds.
The idea is simple: instead of looking at a profile and making assumptions, investigate the projects behind it.
š Live demo: https://repoghost.onrender.com
š» GitHub repository: https://github.com/egbutaify2-ui/repoghost
Why I started building RepoGhost
A GitHub profile can contain dozens of repositories, different technologies, activity records, and projects with very different purposes.
But repository counts and star numbers alone don't tell the whole story.
I wanted to build something that could help answer practical questions:
- What does this GitHub account or organization actually work on?
- Which public repositories are relevant to a particular technology or role?
- What technologies appear in its projects?
- What can recent public activity tell usāand what can't we conclude from it?
- Can I ask follow-up questions about an investigated account instead of starting from scratch?
That last question is especially important to me. I want RepoGhost to feel like an investigation you can continue, not a report you read once and abandon.
How RepoGhost works
The current project combines public GitHub data with AI-assisted analysis.
1. Investigate an account
Enter a GitHub username or organization, such as expressjs. RepoGhost retrieves the public profile and repository information.
2. Follow the evidence
Depending on the investigation, it can surface repository descriptions, programming languages, stars, forks, and visible activity. Repository-level investigations can also examine README files, sampled commits, issues, and releases when available.
3. Ask questions
The goal is to let you ask natural-language questions about the account and its projects, with answers grounded in the collected public evidence.
4. Follow the sources
Claims should lead back to the relevant public GitHub records. If the available information doesn't support an answer, RepoGhost should say what remains unknown rather than inventing a story.
The interesting engineering challenge: AI is not the source of truth
One lesson from building this project is that getting an AI model to return an answer is only part of the job.
The answer also needs to be relevant, concise, supported by evidence, and linked to valid sources.
Models can return malformed output, omit citations, or fail to answer the question directly. A fallback that simply dumps technical errors isn't useful to the person asking the question.
That's why I'm working on making RepoGhost more reliable: validating answers, checking citations against the actual evidence, handling model failures gracefully, and keeping verified GitHub data available even when AI inference fails.
I'd rather RepoGhost admit that it doesn't know than confidently tell someone something the evidence cannot support.
What RepoGhost should never pretend to know
Public GitHub data has limits.
Repository ownership doesn't prove that someone personally wrote every line of code. Recent activity doesn't prove code quality. Stars don't establish engineering ability. And public repositories cannot reveal someone's private work or personal motivations.
RepoGhost is intended to help people investigate evidence, not turn incomplete signals into unquestionable judgments.
Built in the open
I'm developing RepoGhost as part of my work around AI-powered developer tools and evidence-based software analysis.
The project is still evolving, and I'm treating the reliability issues as part of the engineering workānot something to hide behind a nice interface.
Try it with a GitHub account or organization you know. Ask what its projects do, inspect the sources, and see where the evidence leads.
š» Try RepoGhost: https://repoghost.onrender.com
ā Explore the source code: https://github.com/egbutaify2-ui/repoghost
I'd particularly value feedback on one question:
What would make you trust an AI tool that investigates GitHub accounts and explains what it finds?
I'm building toward that standard, one investigation at a time.
Top comments (2)
Surfacing evidence separately from inference is important for this kind of tool. How do you distinguish original work from forks, mirrors or inactive repositories without turning activity counts into a proxy for individual ability?
Thatās a really important point. Thanks for raising it.
My thinking is to separate what GitHub verifies from what RepoGhost infers. For example, we can identify repositories explicitly marked as forks, treat mirrors as a possible classification that needs supporting evidence, and report inactivity using observable signals like last push or release dateāwithout treating inactivity as poor engineering.
I also want to avoid equating repository ownership with individual authorship. Commit history and contribution records can provide useful context, but they still donāt tell the whole story of someoneās ability.
The goal is to surface evidence and its limitations separately, so people can make better-informed judgments rather than receive an arbitrary score. This is exactly the kind of feedback I want to use to make RepoGhost more reliable.