Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We’re kicking off 2025 with everything we've got! 🤩 Introducing CodeGPT's Knowledge Graphs, navigating through the entire Anthropic SDK repository. In this example, we loaded Anthropic Python SDK repository and successfully provided the LLM with all the knowledge it needs to fully understand the codebase. You can leverage these... show more

Daniel San

31,552 subscribers

35,680 views • 1 year ago •via X (Twitter)

Education Science & Technology Music

Anya Rossi• Live Now

Private livecam show

10 Comments

Daniel San1 year ago

Hey @alexalbert__ , we’d love to teach the Anthropic developer community how to use the SDK with our repository knowledge graphs 🌐 Happy to collaborate on something together!

Cris1 year ago

@AnthropicAI I dont think people realize what can be achieved with this 🍰

Arjun1 year ago

@AnthropicAI Looks amazing... I bet this would be more useful than the repo search that Cursor does. @cursor_ai should open up the ecosystem for us to integrate with such tools!

Daniel San1 year ago

@aiguy_arjun @AnthropicAI @cursor_ai We would love to connect our Knowledge Graphs with Cursor... happy to collaborate! 🙌 @cursor_ai @amanrsanger

Rethynk AI1 year ago

@AnthropicAI This is an incredible start to 2025! CodeGPT’s Knowledge Graphs are a game-changer for navigating complex repositories like Anthropic’s SDK. Simplifying codebase understanding for developers will boost productivity and collaboration.

David Olivencia1 year ago

@AnthropicAI Let's GOOOOOOO @codegptAI 🚀 #AI #Copilot #AgenticAI

stijn sagaert1 year ago

@AnthropicAI @VictorTaelin is this something you are looking for to use with your codebase?

🐧 lalo adrian morales 𝕏1 year ago

@AnthropicAI and it looks cool too!

Saïd Aitmbarek1 year ago

@AnthropicAI looks amazing, big fan of ontologies brings a lot of explainability to datasets!

Kekius Optimus1 year ago

@AnthropicAI "In this example, we loaded @AnthropicAI Python SDK repository" Nothing like scratching his own back first, right?

Related Videos

Introducing Codebase Knowledge Graphs in Cursor 🤩 In this video, I’ll walk you through how we went from using a knowledge graph of a repository on the CodeGPT platform to leveraging it directly within the Cursor editor This tool is specifically designed to navigate massive codebases, identify nodes and relationships, and deliver richer context to models specialized in code development, such as Anthropic Claude 3.5 Sonnet Stay tuned for an upcoming tutorial where I'll show you step-by-step how to create knowledge graphs and integrate them seamlessly into your entire software development workflow, from Commits and Pull Requests to even Trello tickets!

Introducing Codebase Knowledge Graphs in Cursor 🤩 In this video, I’ll walk you through how we went from using a knowledge graph of a repository on the CodeGPT platform to leveraging it directly within the Cursor editor This tool is specifically designed to navigate massive codebases, identify nodes and relationships, and deliver richer context to models specialized in code development, such as Anthropic Claude 3.5 Sonnet Stay tuned for an upcoming tutorial where I'll show you step-by-step how to create knowledge graphs and integrate them seamlessly into your entire software development workflow, from Commits and Pull Requests to even Trello tickets!

Daniel San

230,185 views • 1 year ago

You can now use Knowledge Graphs with Claude 3.5 Sonnet in Cursor! 🤩 CodeGPT’s Knowledge Graphs (KG) let you explore your entire codebase. In this case, we're navigating through Anthropic Python SDK. We asked how to send messages in batches and the tool identified the nodes and relationships in all relevant functions and classes. If you're curious about how LLMs will start handling large code repositories, you'll want to start programming CodeGPT’s KGs... I bet Andrej Karpathy will find this fascinating! I hope you get to try them out, because for me, reading documentation feels so 2024... now I just turn repos into KGs and get to work! 🧑🏽‍💻

You can now use Knowledge Graphs with Claude 3.5 Sonnet in Cursor! 🤩 CodeGPT’s Knowledge Graphs (KG) let you explore your entire codebase. In this case, we're navigating through Anthropic Python SDK. We asked how to send messages in batches and the tool identified the nodes and relationships in all relevant functions and classes. If you're curious about how LLMs will start handling large code repositories, you'll want to start programming CodeGPT’s KGs... I bet Andrej Karpathy will find this fascinating! I hope you get to try them out, because for me, reading documentation feels so 2024... now I just turn repos into KGs and get to work! 🧑🏽‍💻

Daniel San

42,005 views • 1 year ago

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

244,238 views • 2 years ago

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

125,928 views • 8 months ago

The OpenAI Codex repo turned into a Knowledge Graph! 🤩 If you want to start working on massive codebases and serious projects, you need to use CodeGPT’s Knowledge Graphs. Here’s a step-by-step 🧵 guide to create your Codex graph and connect it to VSCode 👇

The OpenAI Codex repo turned into a Knowledge Graph! 🤩 If you want to start working on massive codebases and serious projects, you need to use CodeGPT’s Knowledge Graphs. Here’s a step-by-step 🧵 guide to create your Codex graph and connect it to VSCode 👇

Daniel San

179,466 views • 1 year ago

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular open-source Knowledge Graph library for AI agents. 2. Graphiti connects to Neo4j running locally. Now, every time I interact with Cursor, the information is synthesized and stored in the knowledge graph. In short, Cursor now "remembers" everything about our project. Huge! Here is the video I recorded.

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular open-source Knowledge Graph library for AI agents. 2. Graphiti connects to Neo4j running locally. Now, every time I interact with Cursor, the information is synthesized and stored in the knowledge graph. In short, Cursor now "remembers" everything about our project. Huge! Here is the video I recorded.

Santiago

155,401 views • 1 year ago

Exploring Andrej Karpathy Nanochat through a Knowledge Graph Love how this project combines simplicity with power. Want to navigate and understand the entire repo? Check it out here: Plus, you can connect it via MCP to any AI coding assistant and work directly on the repository. Powered by Deep Graph MCP AI at Meta and Groq Inc

Exploring Andrej Karpathy Nanochat through a Knowledge Graph Love how this project combines simplicity with power. Want to navigate and understand the entire repo? Check it out here: Plus, you can connect it via MCP to any AI coding assistant and work directly on the repository. Powered by Deep Graph MCP AI at Meta and Groq Inc

Daniel San

126,557 views • 7 months ago

Introducing Stack Overflow searches with GPT-4o in VSCode This new feature allows you to use the capabilities of /StackOverflow find related posts ensuring a far more accurate answer to your question. There's no waiting list! 🤩 You can use this today! All you have to do is install the CodeGPT extension in VSCode and use OpenAI models (GPT-4o)

Introducing Stack Overflow searches with GPT-4o in VSCode This new feature allows you to use the capabilities of /StackOverflow find related posts ensuring a far more accurate answer to your question. There's no waiting list! 🤩 You can use this today! All you have to do is install the CodeGPT extension in VSCode and use OpenAI models (GPT-4o)

Daniel San

20,105 views • 1 year ago

Introducing Deep Graph Codebase to MCP with One Click... Now Available for Gemini CLI too! 🤩 Transform any public GitHub repository into an AI-ready Code Graph by simply changing the URL from to This instantly prepares the repository for seamless integration with AI assistants. It's that easy! You can now use repositories like ollama as a code graph within any project using Gemini CLI... just add the MCP Server JSON configuration to your .gemini/settings.json file

Introducing Deep Graph Codebase to MCP with One Click... Now Available for Gemini CLI too! 🤩 Transform any public GitHub repository into an AI-ready Code Graph by simply changing the URL from to This instantly prepares the repository for seamless integration with AI assistants. It's that easy! You can now use repositories like ollama as a code graph within any project using Gemini CLI... just add the MCP Server JSON configuration to your .gemini/settings.json file

Daniel San

51,534 views • 11 months ago

Testing Llama 4 in VSCode with CodeGPT! 😱 It scans the entire codebase, reads only the needed files, and gives me the exact run commands 👏 Still in preview… coming soon for all users! Create your free account at

Testing Llama 4 in VSCode with CodeGPT! 😱 It scans the entire codebase, reads only the needed files, and gives me the exact run commands 👏 Still in preview… coming soon for all users! Create your free account at

Daniel San

12,723 views • 1 year ago

Turn any GitHub repository into LLM-ready text! Simply replace "hub" with "ingest" in a GitHub URL and receive a prompt-friendly text ingest for LLMs. Gitingest is 100% open-source and provides: - Directory structure - A brief summary of the project - The entire content as LLM-ready text Plus, it comes with a nice python package and you can run the UI locally! Stay tuned, I'm working on something really cool with this!✨ Link to the GitHub repo in the next tweet! _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on ML and AI Engineering!

Turn any GitHub repository into LLM-ready text! Simply replace "hub" with "ingest" in a GitHub URL and receive a prompt-friendly text ingest for LLMs. Gitingest is 100% open-source and provides: - Directory structure - A brief summary of the project - The entire content as LLM-ready text Plus, it comes with a nice python package and you can run the UI locally! Stay tuned, I'm working on something really cool with this!✨ Link to the GitHub repo in the next tweet! _____ Find me → Akshay 🚀 ✔️ For more insights and tutorials on ML and AI Engineering!

Akshay 🚀

191,226 views • 1 year ago

Introducing Auto Documentation powered by Codebase Knowledge Graphs With CodeGPT, we traverse your entire repo to build a Knowledge Graph that understands how your software works. Capturing relationships between classes, modules, and dependencies. This allows us to generate robust, accurate documentation that misses no detail. We’re helping top companies turn months of documentation work into minutes. ✨ Always in sync with your selected branch. ✨ Updates automatically with every commit. ✨ Generates multiple types of documentation, from technical overviews to function-level docs Currently in preview for selected companies. 👉 Want early access? Apply here:

Introducing Auto Documentation powered by Codebase Knowledge Graphs With CodeGPT, we traverse your entire repo to build a Knowledge Graph that understands how your software works. Capturing relationships between classes, modules, and dependencies. This allows us to generate robust, accurate documentation that misses no detail. We’re helping top companies turn months of documentation work into minutes. ✨ Always in sync with your selected branch. ✨ Updates automatically with every commit. ✨ Generates multiple types of documentation, from technical overviews to function-level docs Currently in preview for selected companies. 👉 Want early access? Apply here:

Daniel San

53,329 views • 1 year ago

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 )

24,435 views • 20 days ago

Introducing the Cline SDK. We rebuilt the Cline harness for our extension and CLI from scratch using all the lessons learned since creating one of the world's first coding agents in 2024, and are open sourcing it for others to build with today. npm i @cline/sdk 🧵

Introducing the Cline SDK. We rebuilt the Cline harness for our extension and CLI from scratch using all the lessons learned since creating one of the world's first coding agents in 2024, and are open sourcing it for others to build with today. npm i @cline/sdk 🧵

Cline

3,564,620 views • 26 days ago

With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!

With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!

Cursor

579,457 views • 17 days ago

That is the easiest way to chat with a complete Github Repository!👀 Replace "github" with "gitingest" in the url, and you get the whole repo as a single string, paste into AI studio and use Google DeepMind Gemini 2.0 Flash Million Token Context video to ask questions! 🤯 Here is how you can chat with the whole python SDK docs. ⬇️

That is the easiest way to chat with a complete Github Repository!👀 Replace "github" with "gitingest" in the url, and you get the whole repo as a single string, paste into AI studio and use Google DeepMind Gemini 2.0 Flash Million Token Context video to ask questions! 🤯 Here is how you can chat with the whole python SDK docs. ⬇️

Philipp Schmid

97,475 views • 1 year ago

$Did these Orthodox monks know something we don't? Religious symbology or fractal antennas? Domed resonators, the use of MERCURY and knowledge of the AETHER... that provided clean ENERGY for this realm. Who built these structures with this knowledge in ancient times? Were these MONKS the original CUSTODIANS? The buildings 'change of use' and the symbols coming to represent something else?$

Did these Orthodox monks know something we don't? Religious symbology or fractal antennas? Domed resonators, the use of MERCURY and knowledge of the AETHER... that provided clean ENERGY for this realm. Who built these structures with this knowledge in ancient times? Were these MONKS the original CUSTODIANS? The buildings 'change of use' and the symbols coming to represent something else?

WhatdoIknow

109,394 views • 2 years ago

Now in VS Code stable: Agent Skills, the open standard created by Anthropic. These folders of instructions, scripts, and resources can be loaded to perform specialized tasks, allowing you to teach the coding agent new capabilities and provide domain-specific knowledge.

Now in VS Code stable: Agent Skills, the open standard created by Anthropic. These folders of instructions, scripts, and resources can be loaded to perform specialized tasks, allowing you to teach the coding agent new capabilities and provide domain-specific knowledge.

Visual Studio Code

116,296 views • 5 months ago

Turn any GitHub repository into a visual treat! Simply replace "hub" with "diagram" in a GitHub URL and instantly view the entire codebase as interactive diagrams for easier understanding. 100% open-source.

Turn any GitHub repository into a visual treat! Simply replace "hub" with "diagram" in a GitHub URL and instantly view the entire codebase as interactive diagrams for easier understanding. 100% open-source.

Akshay 🚀

125,364 views • 1 year ago