Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

🤯 this genius stores his entire codebase syntax in a graph database and queries it so provide context to an llm

Dan McAteer

25,724 subscribers

1,991,499 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Dan Mac

Dan Mac1 год назад

one day things like this will be standard

Фото профиля Milk Road

Milk Road1 год назад

Wall Street ain't ready for this... Coinbase launched Base ~1 year ago This Layer 2 blockchain has raked in ~$1.2M every week on average Now Wall Street is FOMOing into crypto. Front run them by reading Milk Road. 5 minutes. Every day. For free.

Фото профиля kev

kev1 год назад

@Austen Hey that’s me! I’m currently working on v2 of this app and will be launching a public beta in the near future. Anybody is free to shoot me a DM with questions or follow me if they want to hear when the beta drops.

Фото профиля Dan Mac

Dan Mac1 год назад

@Austen that’s awesome Kev - such a cool idea following and looking forward to hearing more about the project!

Фото профиля Gobie Nanthakumar

Gobie Nanthakumar1 год назад

Isn’t that already part of every IDE…like indexing and referencing function definitions?

Фото профиля joey - e/acc 🇿🇦

joey - e/acc 🇿🇦1 год назад

You can do it for free on mordecai, it’s very very simple to implement, it doesn’t make you a genius, it’s called “RAG” and uses a vector database not a graph database.

Фото профиля Shantanu Goel

Shantanu Goel1 год назад

Guy said AST. Tweeter picks up on "syntax" and says guy stores "codebase syntax in a graph database". 🤦‍♂️

Фото профиля Johannes Schmidt 🌌👾

Johannes Schmidt 🌌👾1 год назад

cursor does this, they create embeddings and use them to look up code

Фото профиля Dan Mac

Dan Mac1 год назад

think that’s a little different though embeddings arent legible to a human, whereas a graph is

Фото профиля Saurabh Suri⚡🥷🏼

Saurabh Suri⚡🥷🏼1 год назад

alright you have my attention @taykv2

Фото профиля Bryce DeFigueiredo

Bryce DeFigueiredo1 год назад

@Austen This project brought to you by Velo nicotine pouches

Похожие видео

Bezi is now publicly available. An AI tool designed specifically for game engines, Bezi uses real-time context of your project - codebase, assets, scene graph - to provide tailored development assistance.

Bezi is now publicly available. An AI tool designed specifically for game engines, Bezi uses real-time context of your project - codebase, assets, scene graph - to provide tailored development assistance.

Bezi

37,994 просмотров • 1 год назад

Someone built a tool that converts your entire codebase into a graph database. Instead of dumping code into LLMs, AI can navigate functions, classes, and dependencies like a map. It's called CodeGraphContext.

Someone built a tool that converts your entire codebase into a graph database. Instead of dumping code into LLMs, AI can navigate functions, classes, and dependencies like a map. It's called CodeGraphContext.

Aman

246,889 просмотров • 4 месяцев назад

What would it look like to combine Google search (shallow Knowledge Graph reasoning over an ultra-ultra-wide index) with LLM in-context learning (highly intelligent operations on a tiny index)?

What would it look like to combine Google search (shallow Knowledge Graph reasoning over an ultra-ultra-wide index) with LLM in-context learning (highly intelligent operations on a tiny index)?

Dwarkesh Patel

101,417 просмотров • 1 год назад

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

Mckay Wrigley

85,698 просмотров • 2 лет назад

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,284 просмотров • 2 лет назад

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.

Y Combinator

49,755 просмотров • 8 месяцев назад

RouteLLM - Route To The Best LLM Based On Your Prompt Our RouteLLM got an upgrade this week.., it got smarter at picking the right LLM - o1 for complex queries - gpt4o for quick answers - sonnet for coding - deepseek for simple code - gemini for long context - llama and mini for simple question It optimizes for performance, speed and cost!

RouteLLM - Route To The Best LLM Based On Your Prompt Our RouteLLM got an upgrade this week.., it got smarter at picking the right LLM - o1 for complex queries - gpt4o for quick answers - sonnet for coding - deepseek for simple code - gemini for long context - llama and mini for simple question It optimizes for performance, speed and cost!

Bindu Reddy

17,860 просмотров • 1 год назад

#ChatGPT for your codebase! 🤯 You now can upload your entire codebase/Git repos to #OpenChat & ask #GPT4 to implement anything! With the full context of your code, #OpenChat can answer your questions accurately and effortlessly! Powered by ! 🔥 Link to code ↓

#ChatGPT for your codebase! 🤯 You now can upload your entire codebase/Git repos to #OpenChat & ask #GPT4 to implement anything! With the full context of your code, #OpenChat can answer your questions accurately and effortlessly! Powered by ! 🔥 Link to code ↓

Charly Wargnier

175,644 просмотров • 3 лет назад

i'm building an AI Postgres database studio that connects to your database and generates (and runs) queries based on prompts. i initially built it to be a personal tool but i think others may find it useful. will be releasing v1 soon. here's a quick demo:

i'm building an AI Postgres database studio that connects to your database and generates (and runs) queries based on prompts. i initially built it to be a personal tool but i think others may find it useful. will be releasing v1 soon. here's a quick demo:

zilla builds cool stuff

14,323 просмотров • 7 месяцев назад

I got an LLM to write frontend and backend code for a graph visualizer, fix its own bug and literally deploy it to the public web with google cloud. This would take most devs 2 days. It took AI ~20mins.

I got an LLM to write frontend and backend code for a graph visualizer, fix its own bug and literally deploy it to the public web with google cloud. This would take most devs 2 days. It took AI ~20mins.

Deedy

232,009 просмотров • 1 год назад

🔥 💻 🎥 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

99,719 просмотров • 1 год назад

Query and manipulate dev stores from Shopify CLI Execute queries, mutations, and bulk operations from your terminal Script it, automate it, or hand it off to an agent

Query and manipulate dev stores from Shopify CLI Execute queries, mutations, and bulk operations from your terminal Script it, automate it, or hand it off to an agent

Shopify Developers

16,406 просмотров • 5 месяцев назад

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

55,345 просмотров • 1 месяц назад

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,788 просмотров • 1 год назад

I was able to create this simple CRM with the supabase beta integration in less than an hour. Auth and Database using Supabase 2M tokens used 50mins of pure prompting with the supabase beta now conveniently asks you to allow it to execute database queries to supabase. It also configures necessary policies for you. OMG, StackBlitz you should wrap this up and release it ASAP!

I was able to create this simple CRM with the supabase beta integration in less than an hour. Auth and Database using Supabase 2M tokens used 50mins of pure prompting with the supabase beta now conveniently asks you to allow it to execute database queries to supabase. It also configures necessary policies for you. OMG, StackBlitz you should wrap this up and release it ASAP!

Melvin Vivas

30,408 просмотров • 1 год назад

48 HOURS AFTER KARPATHY POSTED HIS LLM WIKI IDEA, A 26-YEAR-OLD BIRMINGHAM GRAD SHIPPED THE ONE COMMAND THAT MAKES IT WORK. IT NOW HAS 76,000 GITHUB STARS 1 command. 71.5x fewer tokens per query. 0 vector databases points graphify at any folder - codebase, docs, PDFs, screenshots, video. Tree-sitter parses the code, Claude reads the prose, the whole thing lands as a knowledge graph in graphify-out/ one flag - --obsidian - writes the entire graph as a fully-linked Obsidian vault: one markdown note per concept, every relationship a wikilink, every node linked back to its source. Drop the vault into Claude Code as a skill. Claude queries the graph instead of grepping through raw files, forever Safi Shamsi finished his MSc at Birmingham with Distinction in 2025. His thesis was a knowledge-graph RAG system for academic search. He shipped Graphify 48 hours after Karpathy's post, iterates every week, and has already been forked by Rootly AI Labs for incident data. Hacker News, Analytics Vidhya, Towards AI - all organic.76,000 stars. Three months old no neo4j server. no vector db. no embedding pipeline. no cloud. no monthly fee you're reading this on a device that could clone the repo, run one command, and have a Claude-native knowledge graph of your entire codebase in Obsidian before your next standup

48 HOURS AFTER KARPATHY POSTED HIS LLM WIKI IDEA, A 26-YEAR-OLD BIRMINGHAM GRAD SHIPPED THE ONE COMMAND THAT MAKES IT WORK. IT NOW HAS 76,000 GITHUB STARS 1 command. 71.5x fewer tokens per query. 0 vector databases points graphify at any folder - codebase, docs, PDFs, screenshots, video. Tree-sitter parses the code, Claude reads the prose, the whole thing lands as a knowledge graph in graphify-out/ one flag - --obsidian - writes the entire graph as a fully-linked Obsidian vault: one markdown note per concept, every relationship a wikilink, every node linked back to its source. Drop the vault into Claude Code as a skill. Claude queries the graph instead of grepping through raw files, forever Safi Shamsi finished his MSc at Birmingham with Distinction in 2025. His thesis was a knowledge-graph RAG system for academic search. He shipped Graphify 48 hours after Karpathy's post, iterates every week, and has already been forked by Rootly AI Labs for incident data. Hacker News, Analytics Vidhya, Towards AI - all organic.76,000 stars. Three months old no neo4j server. no vector db. no embedding pipeline. no cloud. no monthly fee you're reading this on a device that could clone the repo, run one command, and have a Claude-native knowledge graph of your entire codebase in Obsidian before your next standup

chewa.

295,433 просмотров • 11 дней назад

🚨Recursion🔁 is now LIVE in Desmos!🚨 Now go tell a friend to tell a friend to tell a friend to… → Explore this graph: → Learn more about recursion syntax and see more examples:

🚨Recursion🔁 is now LIVE in Desmos!🚨 Now go tell a friend to tell a friend to tell a friend to… → Explore this graph: → Learn more about recursion syntax and see more examples:

Desmos

23,965 просмотров • 2 лет назад

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

shadow is an open-source background coding agent with a real-time interface and codebase context system here's a breakdown of how it works ⬇️

ishaan dey

21,582 просмотров • 11 месяцев назад

SOLO is giving full-stack energy. We just made some updates to help it build your entire app - front-end, back-end, database, and clean context to tie it all together.

SOLO is giving full-stack energy. We just made some updates to help it build your entire app - front-end, back-end, database, and clean context to tie it all together.

TRAE

22,162 просмотров • 11 месяцев назад

Sharding is the best way to scale a database. But how does it work? And what's the best way to ensure data and queries are evenly distributed? Our interactive article on database sharding teaches you how.

Sharding is the best way to scale a database. But how does it work? And what's the best way to ensure data and queries are evenly distributed? Our interactive article on database sharding teaches you how.

PlanetScale

28,639 просмотров • 3 месяцев назад