14 karma · joined November 15, 2025
I am building and Intelligent Codebase System for AI agents and Developers: https://github.com/devlensio/devlensOSS
Github: https://github.com/devlensio/devlensOSS https://devlens.io
It is open source: https://github.com/devlensio/devlensOSS ; https://devlens.io
It is an open-source project and I will introduce soon its mcp/cli counterpart so that graphical context and sumaries can be given to LLMs/Agents directly through the mcp integration.
Having said that I really hope this model of deepseek, performs significantly on par with the claude saunnet model.
You can star the repo if you like the project. I am still working on cloud version which will have lots of features.
Also the main MOAT of Devlens is not the visualizer but the blast radius feature. Which essentially tells you if I change this file/function where it will affect my Codebase which is specially useful for PR review.
The open source version is live at https://github.com/devlensio/devlensOSS
You can star the repo if you like the project. I am still working on cloud version which will have lots of features.
what depends on this? what else could this affect? how far does this propagate?
usually require a lot of manual tracing across files and components.
So I started building Devlens — a tool that visualizes the codebase as a graph and shows the “blast radius” of components/changes to help with PR reviews, onboarding, and understanding unfamiliar parts of a system.
Curious whether teams here would actually find something like this useful in real workflows, or if this mostly gets solved through experience and familiarity with the codebase over time.
Website: https://devlens.io GitHub: https://github.com/devlensio/devlensOSS
Things like:
what depends on this? what else could this affect? how far does this propagate?
usually require a lot of manual tracing across files and components.
So I started building Devlens — a tool that visualizes the codebase as a graph and shows the “blast radius” of components/changes to help with PR reviews, onboarding, and understanding unfamiliar parts of a system.
Curious whether teams here would actually find something like this useful in real workflows, or if this mostly gets solved through experience and familiarity with the codebase over time.
Website: https://devlens.io GitHub: https://github.com/devlensio/devlensOSS
It visualizes React / Next.js codebases as an interactive graph so you can understand how features and components connect without manually tracing files.
Main focus right now is helping with:
PR reviews (understanding blast radius / impact of changes) onboarding to large codebases understanding unfamiliar parts of a system faster
Also experimenting with summaries + security analysis directly on components.
Still early, but it’s been pretty useful for me so far.
Selling things online was an idea by Amazon, now everyone sells online.
If you really want people not to copy your idea then make something which cannot be easily vibe-coded or copied easily i.e. which require serious skills.
1. You need to focus on the problems that really do exist and for which people might willing to pay for.
2. Marketing and Distribution skills are more Important than your Engineering skills.
3. Good Things take time, if your product is useful and good as well, then it is just a matter of time and marketing. Eventually it will gain traction, so don't loose hope.
I am using claude solely because it's best in terms of Code quality and UI.
According to you do you think codex has surpassed or at least came on par with the claude in terms of code quality and UI ?
How good is codex in terms of code context ?