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.

107,000+ GitHub stars. 5.2M+ downloads. The first open-source project from a YC company to cross 100K⭐mid-batch. Today we launch Graphify Labs (YC S26), the Knowledge Graph engine for enterprises. How would you ship if your AI actually understood your whole codebase?

Safi

6,024 subscribers

112,929 views • 4 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

OpenWork (OpenWork (YC P26)) is the open source alternative to Claude Cowork. Roll out AI compliantly across your non-technical org at scale. Use your existing agents, deploy on-prem, and use any LLM provider you want. They already have 14k stars on GitHub with over 150k downloads. Congrats on the launch, Benjamin Shafii!

OpenWork (OpenWork (YC P26)) is the open source alternative to Claude Cowork. Roll out AI compliantly across your non-technical org at scale. Use your existing agents, deploy on-prem, and use any LLM provider you want. They already have 14k stars on GitHub with over 150k downloads. Congrats on the launch, Benjamin Shafii!

Y Combinator

91,236 views • 4 months ago

We learned how to fly a plane to tell SF one thing. Introducing the Vendo (YC S26) Full-Stack Agentic Interface. A production-ready agent for your users with everything they need. It takes real actions for your users. And it can even build whole new features, micro-apps, and automations, right on top of your product. Built-in permissioning, tool guards, user context, and more. Everything you need for a user-facing agent. One command to install. Open source. Vendo (YC S26) Nour Zahzah

We learned how to fly a plane to tell SF one thing. Introducing the Vendo (YC S26) Full-Stack Agentic Interface. A production-ready agent for your users with everything they need. It takes real actions for your users. And it can even build whole new features, micro-apps, and automations, right on top of your product. Built-in permissioning, tool guards, user context, and more. Everything you need for a user-facing agent. One command to install. Open source. Vendo (YC S26) Nour Zahzah

Yousef

32,623 views • 9 days ago

i quit yc to pursue my side project from college. introducing @schej_it - the easiest way for groups to find a time to meet. it’s open-source and syncs with your calendar.

i quit yc to pursue my side project from college. introducing @schej_it - the easiest way for groups to find a time to meet. it’s open-source and syncs with your calendar.

jonathan liu

238,709 views • 1 year ago

we built this thing called Palmier > it's like a video editor but for ai and open source > generate ai footage using leading models, mix it with your real footage, and connect your Claude to edit videos for you > we used it to make 15+ cinematic yc launch videos > it's free to try today, no waitlist

we built this thing called Palmier > it's like a video editor but for ai and open source > generate ai footage using leading models, mix it with your real footage, and connect your Claude to edit videos for you > we used it to make 15+ cinematic yc launch videos > it's free to try today, no waitlist

Marcos Rico Peng

16,614 views • 2 months ago

We want to see how you build with AI. To better capture that, we've added a new application question for the Spring 2026 batch: The application demo has always been key but now, when you apply to YC, you can upload a markdown file or transcript from Claude Code (or your favorite coding tool). We want to see how you plan, design, debug, and ship your most important features. Apply by Feb 9:

We want to see how you build with AI. To better capture that, we've added a new application question for the Spring 2026 batch: The application demo has always been key but now, when you apply to YC, you can upload a markdown file or transcript from Claude Code (or your favorite coding tool). We want to see how you plan, design, debug, and ship your most important features. Apply by Feb 9:

Y Combinator

205,367 views • 6 months ago

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.

299,885 views • 1 month ago

We got into YC S26 :) The first thing we did was make a list of products we were literally built for. Today, at 12 PM, we're putting that thesis to the test. For the next 12 hours, we'll reach out to every company on that list. The experiment: Can a small YC startup get in front of the biggest AI product teams in the world in a single day? By midnight we'll have the answer. Either way, we'll share the numbers.

We got into YC S26 :) The first thing we did was make a list of products we were literally built for. Today, at 12 PM, we're putting that thesis to the test. For the next 12 hours, we'll reach out to every company on that list. The experiment: Can a small YC startup get in front of the biggest AI product teams in the world in a single day? By midnight we'll have the answer. Either way, we'll share the numbers.

dhruvieiei

42,383 views • 2 months ago

Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their existing production traces & it beat the frontier: +22.9% task success −90.2% latency −94.5% cost If you ever thought of fine-tuning your own model, we'll do it for you, talk to us!

Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their existing production traces & it beat the frontier: +22.9% task success −90.2% latency −94.5% cost If you ever thought of fine-tuning your own model, we'll do it for you, talk to us!

shubham

677,844 views • 2 days ago

Embedder (Embedder) is launching once every week. Our goal is to be the "most launched" company by the end of the YC S25 batch. Today, we're launching large codebase understanding, serial terminal interaction, and a brand new web console for managing your projects. Bob & I have been working with the team a Pebble, the creators of the first smart watch, to make this demo!

Ethan Gibbs

20,358 views • 1 year ago

Opening orders for Reachy Mini today, our open-source desktop robot for AI builders, starting at $299! Fully integrated with LeRobot & Hugging Face for the whole community to build AI apps for it (like this dancing one). We'll probably ship a first batch of a hundred this summer, first come first serve!

Opening orders for Reachy Mini today, our open-source desktop robot for AI builders, starting at $299! Fully integrated with LeRobot & Hugging Face for the whole community to build AI apps for it (like this dancing one). We'll probably ship a first batch of a hundred this summer, first come first serve!

clem 🤗

108,267 views • 1 year ago

🧭nCompass (YC W24) is a platform for simplified hosting & acceleration of open-source LLMs. Its API requires only one line of code to integrate low-latency versions of these models into your AI pipeline. Congrats on the launch Aditya Rajagopal & Diederik Adriaan Vink!

🧭nCompass (YC W24) is a platform for simplified hosting & acceleration of open-source LLMs. Its API requires only one line of code to integrate low-latency versions of these models into your AI pipeline. Congrats on the launch Aditya Rajagopal & Diederik Adriaan Vink!

Y Combinator

10,740 views • 2 years 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

53,516 views • 1 year ago

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

Yarchi

141,580 views • 2 months ago

$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

56,177 views • 2 months ago

Today we're launching Inkbox: the identity and communication layer for AI agents. We give agents their own email, phone, iMessage, and an internet address. Install Inkbox (YC S26) identity with one command: allow anyone to reach your Claude Code, Codex, or Hermes from anywhere, and let it reach anyone.

Today we're launching Inkbox: the identity and communication layer for AI agents. We give agents their own email, phone, iMessage, and an internet address. Install Inkbox (YC S26) identity with one command: allow anyone to reach your Claude Code, Codex, or Hermes from anywhere, and let it reach anyone.

Ray Liao

56,381 views • 1 month 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

155,647 views • 1 year ago

Everyone owns skincare products, but nobody knows what's actually working. Today, Anthea Guo and I launch Lumeria (YC S26) (YC S26) to end that. The Lumoscope is a multispectral camera that clips onto your phone and scans your skin at home with the same light used in clinics, so you see what a mirror can't: a breakout days before it surfaces, and sun damage years before it shows. Every scan is scored on hydration, redness, texture, and sebum, and it compounds into a record of your own skin. Lumi reads that history, connects flare-ups to causes you'd never suspect, and matches products to YOUR data, instead of a population average. Preorders are officially open today at $199 only until Aug 16th. Starting today, skincare will no longer feel like guessing. ☀️

Everyone owns skincare products, but nobody knows what's actually working. Today, Anthea Guo and I launch Lumeria (YC S26) (YC S26) to end that. The Lumoscope is a multispectral camera that clips onto your phone and scans your skin at home with the same light used in clinics, so you see what a mirror can't: a breakout days before it surfaces, and sun damage years before it shows. Every scan is scored on hydration, redness, texture, and sebum, and it compounds into a record of your own skin. Lumi reads that history, connects flare-ups to causes you'd never suspect, and matches products to YOUR data, instead of a population average. Preorders are officially open today at $199 only until Aug 16th. Starting today, skincare will no longer feel like guessing. ☀️

Maryanne Alhallak

1,274,676 views • 9 days ago

I started a company! Introducing Melty, an open source AI code editor for 10x engineers. It's the first editor that understands what you’re doing from the terminal to GitHub and collaborates with you to write production-ready code.

I started a company! Introducing Melty, an open source AI code editor for 10x engineers. It's the first editor that understands what you’re doing from the terminal to GitHub and collaborates with you to write production-ready code.

Charlie Holtz

582,687 views • 1 year ago

We just made AI that reads your mind and automates for you. TrustAI (TrustAI (YC S26)) understands your context across the browser (CRMs, internal tools, Slack, GitHub) and suggests personalized automations you can run in one click. Accept, tweak, or ignore, then keep working while we handle the busywork in the background. The data stays local, and the automations can run up to 47x faster post onboarding than leading competitors. Automations when you need them, built in seconds, one click to run.

We just made AI that reads your mind and automates for you. TrustAI (TrustAI (YC S26)) understands your context across the browser (CRMs, internal tools, Slack, GitHub) and suggests personalized automations you can run in one click. Accept, tweak, or ignore, then keep working while we handle the busywork in the background. The data stays local, and the automations can run up to 47x faster post onboarding than leading competitors. Automations when you need them, built in seconds, one click to run.

Hannah Chung

16,951 views • 1 month ago

Today, we're launching Belvedir (YC S26) We're making private AI models cheap and easy so the world can have trillions of them. Private AI models are cheaper, better, faster, and protect your data from frontier labs, but they're still to expensive and difficult to make for startups and consumers. Belvedir makes private AI models autonomously with less than 5 minutes of setup, so that private AI can finally be accessible to everyone

Today, we're launching Belvedir (YC S26) We're making private AI models cheap and easy so the world can have trillions of them. Private AI models are cheaper, better, faster, and protect your data from frontier labs, but they're still to expensive and difficult to make for startups and consumers. Belvedir makes private AI models autonomously with less than 5 minutes of setup, so that private AI can finally be accessible to everyone

Zachary Yu

85,444 views • 11 days ago