I built an AI coding agent that understands the repository, not just the diff
Most AI coding tools look at the file you changed.
I wanted to know what that change could affect across the repository.
So I’ve been building GitHub Autopilot — an open-source AI engineering agent that can review PRs, fix bugs, scan for security issues, manage GitHub workflows, and now build an AST-based dependency graph of the codebase.
The graph can identify:
- Module dependencies
- Fan-in / fan-out
- Import cycles
- Orphan modules
- Dependency hotspots
- Runtime vs top-level imports
It actually found a 5-module import cycle in my own repository. I fixed it and added CI checks to catch regressions.
The project is open source and self-hostable, with local LLM support for privacy-sensitive code.
GitHub:
What repository-level context do you think AI coding agents are still missing?
0
0 comments
I built an AI coding agent that understands the repository, not just the diff
skool.com/ai-developer-accelerator
Master AI & software development to build apps and unlock new income streams. Transform ideas into profits. 💡➕🤖➕👨💻🟰💰
Leaderboard (30-day)
1
+3
2
+2
3
+1
4
+1
5
+1
Powered by