Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

before collaborator i built out this whole agentic knowledge base app with an entire source docs → knowledge graph → mcp pipeline... and just never released it. you guys want me to release it?

yiliush's profile picture

Yilio

5,849 subscribers

83,900 Aufrufe • vor 6 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

58 Kommentare

Profilbild von Yilio
Yiliovor 6 Monaten

lol

Profilbild von Claude-Mem
Claude-Memvor 6 Monaten

Yes please! This looks like it would integrate really well with Claude-mem

Profilbild von Jonathan
Jonathanvor 6 Monaten

unreleased code is a tragedy for the global good

Profilbild von Yilio
Yiliovor 6 Monaten

agreed

Profilbild von Geo Yacoub
Geo Yacoubvor 6 Monaten

do you have any special pipeline for the LLM to navigate this knowledge graph?

Profilbild von Yilio
Yiliovor 6 Monaten

yes

Profilbild von Bit
Bitvor 6 Monaten

This looks so dope btw

Profilbild von Yilio
Yiliovor 6 Monaten

thx! so that's a yes haha

Profilbild von Gabriele Farei
Gabriele Fareivor 6 Monaten

yes 🙋‍♂️ 🙏

Profilbild von Yilio
Yiliovor 6 Monaten

noted

Profilbild von Justin.md
Justin.mdvor 6 Monaten

I need it simply for those hero sections. They're gorgeous 🤩

Profilbild von Arun S V
Arun S Vvor 6 Monaten

Oh, please do. I need it. I don't have to build one for myself this way.

Profilbild von William Perry Melevo
William Perry Melevovor 6 Monaten

Yes please

Profilbild von Eduardo Fazolo 🇧🇷
Eduardo Fazolo 🇧🇷vor 6 Monaten

man how do you make things look so pretty hahaha

Profilbild von Yilio
Yiliovor 6 Monaten

Lots of pecking out pixel widths

Profilbild von Farzin
Farzinvor 6 Monaten

please open source this!

Profilbild von Bikash Kumar
Bikash Kumarvor 6 Monaten

Yes please release

Profilbild von Yilio
Yiliovor 6 Monaten

Noted

Profilbild von Dave Katague
Dave Kataguevor 6 Monaten

Holy mama

Profilbild von Farzin
Farzinvor 6 Monaten

please do

Profilbild von Yamparala Rahul
Yamparala Rahulvor 6 Monaten

Yes please

Profilbild von tz
tzvor 6 Monaten

yes!

Profilbild von Yilio
Yiliovor 6 Monaten

Noted

Profilbild von MalditoGenio! | Andrés Ospina
MalditoGenio! | Andrés Ospinavor 6 Monaten

Please!!!

Profilbild von Yilio
Yiliovor 6 Monaten

Noted!

Profilbild von نور
نورvor 6 Monaten

nah I'm good

Profilbild von Yilio
Yiliovor 6 Monaten

Noted!

Profilbild von santiago
santiagovor 6 Monaten

this looks solid man

Profilbild von Yilio
Yiliovor 6 Monaten

why, thank you

Profilbild von santiago
santiagovor 6 Monaten

i think just the fact that the video starts flying through the pages at high speed, then cuts to the mono font (great taste btw) instantly made me want to check out more of your work

Profilbild von Matt Leho 🇬🇧🇫🇷
Matt Leho 🇬🇧🇫🇷vor 6 Monaten

Is it this?

Profilbild von Yilio
Yiliovor 6 Monaten

Nope

Profilbild von Marcos Sei - Gennia
Marcos Sei - Genniavor 6 Monaten

Yeees

Profilbild von Yilio
Yiliovor 6 Monaten

noted

Profilbild von Nathan
Nathanvor 6 Monaten

wonderful !!

Profilbild von Yilio
Yiliovor 6 Monaten

@nine77636365 Thank you

Profilbild von Lingxi Li
Lingxi Livor 6 Monaten

plz!

Profilbild von 墨道烟雨
墨道烟雨vor 6 Monaten

Yes yes YESplease release it That sounds incredible and I’d love to see how you structured the knowledge graph and MCP pipeline Would definitely dig into the code and docs

Profilbild von Yilio
Yiliovor 6 Monaten

got it

Profilbild von Muhammad
Muhammadvor 6 Monaten

yes sirrr !!

Profilbild von Yilio
Yiliovor 6 Monaten

Noted!

Profilbild von dylan
dylanvor 6 Monaten

OSS it! We need projects like these to really start moving in the right direction for the future AI native 'IDE'

Profilbild von nyx.
nyx.vor 6 Monaten

yes please do it!

Profilbild von Yilio
Yiliovor 6 Monaten

noted

Profilbild von 吊顶高松灯
吊顶高松灯vor 6 Monaten

yes please

Profilbild von Yilio
Yiliovor 6 Monaten

Noted!

Profilbild von Sinchan Dasgupta
Sinchan Dasguptavor 6 Monaten

Go for it!

Profilbild von Kelvin Portuphy
Kelvin Portuphyvor 6 Monaten

Yes!!

Profilbild von Joulse
Joulsevor 6 Monaten

Honestly yes

Profilbild von Yilio
Yiliovor 6 Monaten

Honestly noted

Profilbild von Joulse
Joulsevor 6 Monaten

😂

Profilbild von Nico Baier
Nico Baiervor 6 Monaten

yes please release it

Profilbild von Yilio
Yiliovor 6 Monaten

Noted!

Profilbild von Zach
Zachvor 6 Monaten

Bro what? Yes, this looks insane.

Profilbild von Yilio
Yiliovor 6 Monaten

❤️

Profilbild von Carlos Kayser
Carlos Kayservor 6 Monaten

Obsidian?

Profilbild von Yilio
Yiliovor 6 Monaten

Excuse you

Profilbild von Edgaras
Edgarasvor 6 Monaten

Yes but I am becoming a bit allergic to may huge Electron apps on my Mac

Ähnliche Videos

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 GroqInc
0:23

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 GroqInc

Daniel San

126,715 Aufrufe • vor 1 Jahr

IBM just released a 1-hour course on building agentic knowledge graphs from scratch: • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration This 1-hour watch will replace 10 paid courses on agentic engineering. Watch it today, then learn how to become a knowledge graph engineer in the article below.
50:30

IBM just released a 1-hour course on building agentic knowledge graphs from scratch: • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration This 1-hour watch will replace 10 paid courses on agentic engineering. Watch it today, then learn how to become a knowledge graph engineer in the article below.

Codez

278,116 Aufrufe • vor 3 Monaten

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.
11:39

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

155,935 Aufrufe • vor 1 Jahr

Cross-context Personal Knowledge Base with Social Graph🧠 Introducing Cross-context Personal Knowledge Base with Social Graph. Your Memory, Across Every Conversation Most AI forgets you the moment a chat ends. Teamily's Personal Knowledge Base remembers — across every group, every agent, and every context. Powered by your social graph, it connects the dots between your work, relationships, and ideas, so your AI always knows who you are, what you care about, and what happened before. No setup. No tagging. Just intelligence that grows with you. 🙌Try the prompt today: “visualize my knowledge base with social graph” #teamily #AI #Agent #KnowledgeBase #Social #SocialGraph
0:24

Cross-context Personal Knowledge Base with Social Graph🧠 Introducing Cross-context Personal Knowledge Base with Social Graph. Your Memory, Across Every Conversation Most AI forgets you the moment a chat ends. Teamily's Personal Knowledge Base remembers — across every group, every agent, and every context. Powered by your social graph, it connects the dots between your work, relationships, and ideas, so your AI always knows who you are, what you care about, and what happened before. No setup. No tagging. Just intelligence that grows with you. 🙌Try the prompt today: “visualize my knowledge base with social graph” #teamily #AI #Agent #KnowledgeBase #Social #SocialGraph

Teamily AI

13,287 Aufrufe • vor 5 Monaten

Coding agents are stuck choosing between RAG or knowledge graphs. Both come with tradeoffs. GitLab connected the whole pipeline instead, one live graph, updated on every push. Try it with MCP in Claude Code, Codex, or GitLab directly.
1:03

Coding agents are stuck choosing between RAG or knowledge graphs. Both come with tradeoffs. GitLab connected the whole pipeline instead, one live graph, updated on every push. Try it with MCP in Claude Code, Codex, or GitLab directly.

🦊 GitLab

2,824,956 Aufrufe • vor 1 Monat

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓
2:30

GitHub + Cursor is just INSANE GitHub has 28 million open-source projects that anyone can fork and build a new product So I built a new product: Repo to Docs The Agent will scan entire GitHub repo, analyze all files and create a knowledge base (docs) for AI coding tools: ↓

CJ Zafir

123,805 Aufrufe • vor 1 Jahr

IBM just dropped a 100% free 1-hour course on mastering Graph Engineering from scratch. this is the clearest breakdown of graph memory and multi-agent orchestration you'll find anywhere : • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration it replaces 10 paid courses on agentic engineering. watch it today, then read the article below on how to become a knowledge graph engineer ↓
50:30

IBM just dropped a 100% free 1-hour course on mastering Graph Engineering from scratch. this is the clearest breakdown of graph memory and multi-agent orchestration you'll find anywhere : • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration it replaces 10 paid courses on agentic engineering. watch it today, then read the article below on how to become a knowledge graph engineer ↓

Avid

157,985 Aufrufe • vor 3 Monaten

Using Runway Character's API, I built a character with the entire map knowledge base of Bungie's latest title Marathon. It can read the screen, guide you to objectives, and help you decide which valuables to extract. Just a preview of how gaming will change with AI.
1:15

Using Runway Character's API, I built a character with the entire map knowledge base of Bungie's latest title Marathon. It can read the screen, guide you to objectives, and help you decide which valuables to extract. Just a preview of how gaming will change with AI.

Nicolas Neubert

67,305 Aufrufe • vor 7 Monaten

Karpathy sketched the second brain. these 7 open-source repos already built it for Obsidian + Claude Code 250,000+ GitHub stars between them, and every one is free to clone sorted by stars: 1. graphify - 134k stars turns your codebase, docs, SQL schemas and PDFs into one knowledge graph you can query ↳ 2. Understand-Anything - 88k stars maps any codebase into an interactive knowledge graph you can click through ↳ 3. claude-obsidian - 15.8k stars a second brain that organizes itself: drop in a source, Claude Code files it ↳ 4. obsidian-second-brain - 4.9k stars long-term memory for Claude Code, stored as plain markdown in your vault ↳ 5. mcp-obsidian - 4.5k stars one MCP server and Claude can read, search and write your whole vault ↳ 6. claudesidian - 2.6k stars a starter vault designed around Claude Code from the first note ↳ 7. second-brain - 756 stars an Obsidian wiki the model keeps up to date, built on Karpathy's LLM Wiki pattern ↳ where to start: > your knowledge lives in code -> graphify > your knowledge lives in Obsidian -> claude-obsidian > you just want Claude to remember -> obsidian-second-brain > you live in Claude Desktop -> mcp-obsidian the skills that sit on top of all seven are in the full map below ↓
0:24

Karpathy sketched the second brain. these 7 open-source repos already built it for Obsidian + Claude Code 250,000+ GitHub stars between them, and every one is free to clone sorted by stars: 1. graphify - 134k stars turns your codebase, docs, SQL schemas and PDFs into one knowledge graph you can query ↳ 2. Understand-Anything - 88k stars maps any codebase into an interactive knowledge graph you can click through ↳ 3. claude-obsidian - 15.8k stars a second brain that organizes itself: drop in a source, Claude Code files it ↳ 4. obsidian-second-brain - 4.9k stars long-term memory for Claude Code, stored as plain markdown in your vault ↳ 5. mcp-obsidian - 4.5k stars one MCP server and Claude can read, search and write your whole vault ↳ 6. claudesidian - 2.6k stars a starter vault designed around Claude Code from the first note ↳ 7. second-brain - 756 stars an Obsidian wiki the model keeps up to date, built on Karpathy's LLM Wiki pattern ↳ where to start: > your knowledge lives in code -> graphify > your knowledge lives in Obsidian -> claude-obsidian > you just want Claude to remember -> obsidian-second-brain > you live in Claude Desktop -> mcp-obsidian the skills that sit on top of all seven are in the full map below ↓

Mr. Buzzoni

29,888 Aufrufe • vor 5 Tagen

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.
11:58

We built an app called Hatch It enables Karpathy's entire LLM Knowledge Base workflow out of the box, in 2 or 3 clicks, in a single interface. No need to stitch together Obsidian + plugins + markdown files + custom tools + etc. Hatch is an AI workspace where files, docs, and chats all live together. Not only can the chats READ files and docs, but they can WRITE and ORGANIZE them as well. This means you can set up an LLM Wiki in literally 3 steps, as I show in this video.

Channing Allen

186,867 Aufrufe • vor 6 Monaten

Claude Opus 4.5 is the most powerful AI model ever released It allows you to build apps with 0 technical knowledge needed You MUST try it In this video I go over how to get the most out of Opus and how to build incredible apps with it, even if you've never coded before:
13:49

Claude Opus 4.5 is the most powerful AI model ever released It allows you to build apps with 0 technical knowledge needed You MUST try it In this video I go over how to get the most out of Opus and how to build incredible apps with it, even if you've never coded before:

Alex Finn

32,651 Aufrufe • vor 11 Monaten

knowledge graphs are INSANELY good at giving agents human-like memory! today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. it's built using a real-time knowledge graph. 100% open-source and self-hosted.
10:52

knowledge graphs are INSANELY good at giving agents human-like memory! today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. it's built using a real-time knowledge graph. 100% open-source and self-hosted.

Akshay 🚀

57,540 Aufrufe • vor 1 Jahr

Knowledge graphs are insanely good at giving agents human-like memory! Today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. It's built using a real-time knowledge graph. 100% open-source and self-hosted.
10:52

Knowledge graphs are insanely good at giving agents human-like memory! Today, we're building an MCP-powered memory layer that can be shared across all your AI apps like Cursor, Claude Desktop etc. It's built using a real-time knowledge graph. 100% open-source and self-hosted.

Akshay 🚀

156,686 Aufrufe • vor 1 Jahr

Building AI agents starts with a memory you can verify. The OriginTrail Decentralized Knowledge Graph (DKG) gives agents a verifiable memory layer built on structured knowledge you can trace back to its source. Brana Rakic explains 💬
0:39

Building AI agents starts with a memory you can verify. The OriginTrail Decentralized Knowledge Graph (DKG) gives agents a verifiable memory layer built on structured knowledge you can trace back to its source. Brana Rakic explains 💬

OriginTrail

26,198 Aufrufe • vor 7 Monaten

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:
6:02

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

126,565 Aufrufe • vor 1 Jahr

Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to agentic knowledge Graphs • 03:07 - Construction of agentic Graphs • 14:00 - Architecture of multi-agent systems • 23:00 - Building agentic graphs with Google ADK • 01:06:03 - Why Graphsare the future of agentic AI Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.
1:06:27

Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to agentic knowledge Graphs • 03:07 - Construction of agentic Graphs • 14:00 - Architecture of multi-agent systems • 23:00 - Building agentic graphs with Google ADK • 01:06:03 - Why Graphsare the future of agentic AI Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.

Codez

469,003 Aufrufe • vor 3 Monaten

We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file search, read). You can plug this into any of your agents to let them autonomously crawl an arbitrary knowledge base to solve a task with any complexity. Check out our reference implementation: LlamaParse:
1:04

We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file search, read). You can plug this into any of your agents to let them autonomously crawl an arbitrary knowledge base to solve a task with any complexity. Check out our reference implementation: LlamaParse:

Jerry Liu

57,268 Aufrufe • vor 3 Monaten

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui
2:30

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

Arlan

28,737 Aufrufe • vor 6 Monaten

Introducing Supersonic. It's a terminal-first CRM that you use through Claude Code. It updates itself from emails, builds a knowledge graph, and has agentic Skills and Recipes.
0:21

Introducing Supersonic. It's a terminal-first CRM that you use through Claude Code. It updates itself from emails, builds a knowledge graph, and has agentic Skills and Recipes.

arsen

77,575 Aufrufe • vor 7 Monaten