正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

New skill to understand any codebase /𝚍𝚒𝚏𝚏𝚒𝚝𝚢-𝚝𝚘𝚞𝚛 [𝚊𝚗𝚢 𝚏𝚎𝚊𝚝𝚞𝚛𝚎] Get an interactive AI walkthrough of every part of the codebase that touches that feature.

Kamran Ahmed

45,996 subscribers

30,234 次观看 • 7 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 条评论

Kamran Ahmed 的头像

Kamran Ahmed7 个月前

Try it out 👇

FileCity 的头像

FileCity7 个月前

Great work! @kamrify Made you a visual map + narrated walkthrough of diffity: A GitHub-style diff viewer and code review tool for AI coding agents. Lets agents (Claude Code, Cursor, etc.) review changes, leave inline comments, and auto-apply fixes in a clean browser interface.

Cyrus 的头像

Cyrus7 个月前

@kamrify Very cool!

Srinivasan K K 的头像

Srinivasan K K7 个月前

@kamrify Really needed for any devs.

Mathew Chan 的头像

Mathew Chan7 个月前

@kamrify Very cool, nice work 🙌

shashwa7 的头像

shashwa77 个月前

@kamrify Such a solid use-case!

Jacek 的头像

Jacek7 个月前

@kamrify Looks amazing!

Andrew Qu 的头像

Andrew Qu7 个月前

@kamrify pretty cool

Thomas Tao 的头像

Thomas Tao7 个月前

@kamrify The feature scoped walkthrough is the part that feels right. Full repo summaries usually blur fast. I’ve had better luck when the unit of understanding is one user facing change and the files around it. Probably closer to how teams actually build context anyway.

Sailon 🔮 的头像

Sailon 🔮7 个月前

@kamrify The next wedge in coding tools is repo legibility, not just codegen. Models can already write plenty of code. The real leverage is getting humans and agents to the exact slice of architecture, ownership, and blast radius fast enough to intervene confidently.

RepoWise 的头像

RepoWise7 个月前

@kamrify This is cool for exploring features interactively. The flip side is giving AI tools that same deep understanding automatically. Walkthrough for humans + structured context for AI = the full picture.

Saleh 的头像

Saleh7 个月前

@kamrify Which software you use for screen recordings?

Saeed Anwar 的头像

Saeed Anwar7 个月前

@kamrify Interactive feature-level codebase walkthrough is exactly what onboarding needed. "Show me everything that touches payment processing" is infinitely more useful than grep. This is the kind of tooling that makes large codebases actually manageable.

Reasonable Minds Can Differ 的头像

Reasonable Minds Can Differ7 个月前

@kamrify Dude just casually solved cognitive debt

相关视频

/readout in Warp Turns any research question you have about your codebase into an interactive HTML file with architecture diagram and linked file references that you can share with your teammates! skill linked below, courtesy of zach bai

/readout in Warp Turns any research question you have about your codebase into an interactive HTML file with architecture diagram and linked file references that you can share with your teammates! skill linked below, courtesy of zach bai

sathvik

17,108 次观看 • 3 个月前

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

Google NotebookLM is absolutely insane, easily the best AI product out there, and it is free to use. The new Mindmap feature makes learning so easy. You can use it to understand your codebase. Just convert your codebase to a single file and try it out.

AshutoshShrivastava

241,207 次观看 • 1 年前

If you understand your whole codebase, the codebase isn't that important. Real software is larger than what your brain can comprehend.

If you understand your whole codebase, the codebase isn't that important. Real software is larger than what your brain can comprehend.

Theo - t3.gg

2,716,985 次观看 • 1 个月前

WebMCP is a game changer for browser agents I built a skill that adds WebMCP support to any codebase - in this demo, I turned Excalidraw into an agent-native experience in a few minutes then I used Stagehand to control the canvas and draw anything. works on any open-source codebase

WebMCP is a game changer for browser agents I built a skill that adds WebMCP support to any codebase - in this demo, I turned Excalidraw into an agent-native experience in a few minutes then I used Stagehand to control the canvas and draw anything. works on any open-source codebase

Shrey Pandya

13,922 次观看 • 2 个月前

how to understand a codebase from the first principles. (example with a real production codebase)

how to understand a codebase from the first principles. (example with a real production codebase)

Ajeet ( opensox.ai )

25,358 次观看 • 5 个月前

Marge Simpson - sMITten Recursive Context Engine Is now a FULL Featured - AI AGNOSTIC- Drop-in AI workflow for: - Automated audits - Bug fixes - New feature SUGGESTIONS - New feature IMPLEMENTATION - Complete Automated Testing for any codebase. BEATS ralph every time. #Claude #OpenAI #Marge #Antigravity #VSCode #RalphWiggum

Marge Simpson - sMITten Recursive Context Engine Is now a FULL Featured - AI AGNOSTIC- Drop-in AI workflow for: - Automated audits - Bug fixes - New feature SUGGESTIONS - New feature IMPLEMENTATION - Complete Automated Testing for any codebase. BEATS ralph every time. #Claude #OpenAI #Marge #Antigravity #VSCode #RalphWiggum

J. Peg Getty

90,347 次观看 • 9 个月前

“The downside of not having a clean codebase is worse than ever.” just watched an interview from dax explaining why OpenCode’s codebase is now cleaner than it’s ever been. an agent’s performance is a function of its intelligence, your instruction, and its context (the codebase). that’s why it’s more important than ever to maintain the codebase regularly, establish patterns, and go back to fix some of the old deprecated ways.

“The downside of not having a clean codebase is worse than ever.” just watched an interview from dax explaining why OpenCode’s codebase is now cleaner than it’s ever been. an agent’s performance is a function of its intelligence, your instruction, and its context (the codebase). that’s why it’s more important than ever to maintain the codebase regularly, establish patterns, and go back to fix some of the old deprecated ways.

ℏεsam

110,824 次观看 • 3 个月前

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇

Dan McAteer

99,802 次观看 • 1 年前

introducing knowledge bases. greptile maintains detailed docs about how your codebase works, and uses them during review. for each part of the codebase, it maintains a running list of past bugs. this way, the next time it reviews that part of the code, it knows what to look for. greptile catches 12.2% more bugs with knowledge bases enabled! now available to all users :)

introducing knowledge bases. greptile maintains detailed docs about how your codebase works, and uses them during review. for each part of the codebase, it maintains a running list of past bugs. this way, the next time it reviews that part of the code, it knows what to look for. greptile catches 12.2% more bugs with knowledge bases enabled! now available to all users :)

Daksh Gupta

31,556 次观看 • 2 个月前

Introducing chat on arXiv papers with codebase context 🔥 Understand papers deeply by exploring the code that powers them

Introducing chat on arXiv papers with codebase context 🔥 Understand papers deeply by exploring the code that powers them

alphaXiv

64,228 次观看 • 1 年前

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Dipanjan Dey

2,075,624 次观看 • 1 年前

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

175,308 次观看 • 4 个月前

visualize any codebase 👀

visualize any codebase 👀

Ahmed Khaleel

1,198,538 次观看 • 1 年前

Claude Code Unpacked! Visual walkthrough of the entire 500k-line leaked codebase. What happens when you type a message: - the agent loop - 50+ tools - multi-agent orchestration - unreleased features Want to understand the internals or build your own agent harness? start here:

Claude Code Unpacked! Visual walkthrough of the entire 500k-line leaked codebase. What happens when you type a message: - the agent loop - 50+ tools - multi-agent orchestration - unreleased features Want to understand the internals or build your own agent harness? start here:

Akshay 🚀

24,552 次观看 • 7 个月前

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.

Jason Zhou

81,271 次观看 • 4 个月前

I found an excellent use case for Remotion & claude code - get it to create a video explaining how the codebase works. In this case I got it to explain how codebase works

I found an excellent use case for Remotion & claude code - get it to create a video explaining how the codebase works. In this case I got it to explain how codebase works

Peter Gostev

15,379 次观看 • 9 个月前

Your codebase gets harder to maintain with every feature you ship. Kieran Klaassen's gets easier. He built compound engineering, and Every adopted it company-wide. The difference is compounding.

Your codebase gets harder to maintain with every feature you ship. Kieran Klaassen's gets easier. He built compound engineering, and Every adopted it company-wide. The difference is compounding.

Every 📧

83,671 次观看 • 7 个月前