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.

I built the graph engineering pipeline instead of just reading about it. had to share what i found THE ENTIRE GRAPH ENGINEERING PIPELINE—ROOTED IN REAL, OPEN-SOURCE BUILDING, NOT SLIDES. Representation. Ontologies. Entity extraction. Relationships. Events. QA gate. Fusion. Embeddings. Actual memory your agent can navigate instead of hand-waving. And... the best part: the end-to-end path already exists in public repos. Strwythura lays out the full ontology workflow, including entity resolution plus embedding-boosted GraphRAG. llm2kg tackles entity + relation extraction aligned to an ontology, persists it in Neo4j with vector embeddings, and ships a ReAct agent that queries the graph directly. No “coming soon.” Just working code you can point at your own data today.show more

CyrilXBT

196,769 subscribers

12,800 views • 3 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Comments

mufettis 🐋3 days ago

the open source angle makes this even better

Yaki3 days ago

the QA gate is where graph memory earns trust imo

Yanyan L3 days ago

everyone's posting the graph diagram, nobody's posting the QA gate that catches the garbage entities 💙 the gate is the whole thing

Macro Bombastic3 days ago

yeah the pipeline is one thing, the qa gate is what actually saves you tbh

Oladosu Enitan3 days ago

I spend more effort giving each trade idea a review deadline and less effort predicting every candle.

magsimich3 days ago

building the whole pipeline is way better than just reading about it

Colbert3 days ago

Building is always the best way to learn. There is too much theory out there and not enough people actually shipping the pipeline.

Sami3 days ago

include one deliberately ambiguous entity in the demo and show whether the QA gate rejects it or merges it

Lea Thompson3 days ago

barely readable text wall. the font on this is a crime

Related Videos

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

holy sh*t this is actually free graph engineering is about to be the most valuable skill in AI... and an entire university program on it is public on GitHub it's a full graduate course on knowledge graphs, lecture by lecture the pipeline, end to end: representation → ontology → entity extraction → relations → events → quality gate → fusion → embeddings → memory your agent can traverse I compressed that path into a Claude skill: 1. clone the repo 2. hand the skill to Claude 3. done, it walks you through the whole pipeline on your own project save and bookmark this no matter what 👇

darkzodchi

51,527 views • 1 month ago

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Ricker

19,652 views • 11 days ago

Google Senior Engineer Annie Wang just dropped a free hands-on course on Graph RAG agents, from scratch: Setup → Graph Schema → Embeddings → Hybrid Search (RRF) → ADK Agent → Deploy 0% → 0:00 – a Graph RAG agent with ADK 25% → 13:01 – Build the graph schema and visualize your data 77% → 39:16 – Hybrid search + RRF 84% → 43:05 – Wiring up the ADK agent: runner, session service, memory service 100% → 51:06 – Final demo and deploying the agent with FastAPI This is one of the few guides that walks through real code and architecture, from an empty project to a working agent. Watch it, then build it yourself

Google Senior Engineer Annie Wang just dropped a free hands-on course on Graph RAG agents, from scratch: Setup → Graph Schema → Embeddings → Hybrid Search (RRF) → ADK Agent → Deploy 0% → 0:00 – a Graph RAG agent with ADK 25% → 13:01 – Build the graph schema and visualize your data 77% → 39:16 – Hybrid search + RRF 84% → 43:05 – Wiring up the ADK agent: runner, session service, memory service 100% → 51:06 – Final demo and deploying the agent with FastAPI This is one of the few guides that walks through real code and architecture, from an empty project to a working agent. Watch it, then build it yourself

Morty

17,524 views • 2 days ago

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

Hanako

53,692 views • 1 month ago

Google just released 1-hour workshop on "Graph Engineering" for agentic systems from 0% to 100%: "loop agent is getting deprecated soon, so I’m going to focus on graph workflows" 0% → 8:01 - build your first agent from scratch 30% → 24:14 - Prompt engineering 55% → 44:48 - Graphs: kill the tree, draw the graph 80% → 1:00:47 - the router that never asks the model 100% → 1:19:49 - Parallel engineering: fan out without losing control most agent tutorials tell you to add another agent - this one deletes three of them and puts plain functions in their place watch it, open the lab, build the graph - then read the full architecture below ↓

Google just released 1-hour workshop on "Graph Engineering" for agentic systems from 0% to 100%: "loop agent is getting deprecated soon, so I’m going to focus on graph workflows" 0% → 8:01 - build your first agent from scratch 30% → 24:14 - Prompt engineering 55% → 44:48 - Graphs: kill the tree, draw the graph 80% → 1:00:47 - the router that never asks the model 100% → 1:19:49 - Parallel engineering: fan out without losing control most agent tutorials tell you to add another agent - this one deletes three of them and puts plain functions in their place watch it, open the lab, build the graph - then read the full architecture below ↓

codila

22,633 views • 1 month ago

A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone. most people are still building agents the way that's about to be obsolete. > why single-agent loops break and go "goal blind" > the 4 parts of a graph: nodes, edges, state, policy > 3 topologies that run everything: diamond, supervisor, pipeline > Anthropic's 5 official workflow patterns the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors. I broke the same architecture down with Kimi K3. Full A-Z guide below.

A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone. most people are still building agents the way that's about to be obsolete. > why single-agent loops break and go "goal blind" > the 4 parts of a graph: nodes, edges, state, policy > 3 topologies that run everything: diamond, supervisor, pipeline > Anthropic's 5 official workflow patterns the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors. I broke the same architecture down with Kimi K3. Full A-Z guide below.

Kirill

2,725,404 views • 1 month ago

Andrew Ng just released a 1-hour course on what comes after RAG. How to turn raw documents into agent memory: 00:00 - Why larger context windows are not enough 02:18 - Extract entities, relationships, and sources 14:31 - Coordinate specialized agents inside one graph 30:43 - Build it with Google ADK and Neo4j 47:25 - Turn knowledge graphs into persistent memory Most people are still learning RAG. Andrew Ng is already teaching the layer that comes after it. Documents → Entities → Relationships → Agents → Knowledge Graph More context is the old workflow. Persistent graphs are the new memory layer. This 1-hour watch is worth more than most paid GraphRAG courses. Bookmark and watch it today Then read the full graph engineering roadmap below

Andrew Ng just released a 1-hour course on what comes after RAG. How to turn raw documents into agent memory: 00:00 - Why larger context windows are not enough 02:18 - Extract entities, relationships, and sources 14:31 - Coordinate specialized agents inside one graph 30:43 - Build it with Google ADK and Neo4j 47:25 - Turn knowledge graphs into persistent memory Most people are still learning RAG. Andrew Ng is already teaching the layer that comes after it. Documents → Entities → Relationships → Agents → Knowledge Graph More context is the old workflow. Persistent graphs are the new memory layer. This 1-hour watch is worth more than most paid GraphRAG courses. Bookmark and watch it today Then read the full graph engineering roadmap below

Lunar

42,118 views • 1 month 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 • 3 months ago

Microsoft has released an open-source tool that helps teams learn ontology design before choosing a knowledge graph platform. It is called Ontology Playground. The project is a fully static React app, which means it does not need a backend, account system, database, or hosted service to run. The goal is simple: Help people understand what goes inside a graph before they buy or build the graph database. Ontology Playground includes six pre-built domain ontologies: → Retail → Healthcare → Finance → Manufacturing → E-Commerce → Education Each one gives users a starting point for understanding entities, relationships, properties, and how domain knowledge gets structured. The app also includes a live visual designer, structured learning paths, hands-on labs, and RDF/XML export for Fabric IQ. Because it is static, it can be deployed almost anywhere. No backend. No vendor lock-in. No platform commitment upfront. This matters because many teams jump into knowledge graphs too early. They focus on the database first. But the harder question is usually: What should the graph actually know? Ontology Playground teaches that layer first.

Microsoft has released an open-source tool that helps teams learn ontology design before choosing a knowledge graph platform. It is called Ontology Playground. The project is a fully static React app, which means it does not need a backend, account system, database, or hosted service to run. The goal is simple: Help people understand what goes inside a graph before they buy or build the graph database. Ontology Playground includes six pre-built domain ontologies: → Retail → Healthcare → Finance → Manufacturing → E-Commerce → Education Each one gives users a starting point for understanding entities, relationships, properties, and how domain knowledge gets structured. The app also includes a live visual designer, structured learning paths, hands-on labs, and RDF/XML export for Fabric IQ. Because it is static, it can be deployed almost anywhere. No backend. No vendor lock-in. No platform commitment upfront. This matters because many teams jump into knowledge graphs too early. They focus on the database first. But the harder question is usually: What should the graph actually know? Ontology Playground teaches that layer first.

Ryan Hart

246,540 views • 1 month ago

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 views • 1 month ago

Today we're launching Jitsu MCP. This is an MCP server that lets your agent run your entire event pipeline directly in Claude Code, Claude Desktop, Cursor, or VS Code. Here's how it works: Add the server: claude mcp add --transport http jitsu Run this prompt: "Route my web stream into ClickHouse, but only purchase and signup events. Send a test event, check Live Events, and if anything errors, find the function in the path and fix it." Approve the OAuth prompt once, and all 26 tools are live Your agent wires the streams, watches Live Events, and rewrites a function when one of them throws. It runs the fix against a real event before shipping it, so nothing is persisted until it works. Every change lands in the audit log tagged mcp, so you can tell what the agent did from what a person did. It's all MIT licensed, and it runs against your own deployment. Jitsu is one of the fastest growing open-source CDPs with 5,000+ GitHub stars. Capturing events is unlimited and free, and delivery is free up to 200k events a month. Comment Jitsu and I'll DM you the exact prompts I run in Claude Code to build an event pipeline end to end.

Today we're launching Jitsu MCP. This is an MCP server that lets your agent run your entire event pipeline directly in Claude Code, Claude Desktop, Cursor, or VS Code. Here's how it works: Add the server: claude mcp add --transport http jitsu Run this prompt: "Route my web stream into ClickHouse, but only purchase and signup events. Send a test event, check Live Events, and if anything errors, find the function in the path and fix it." Approve the OAuth prompt once, and all 26 tools are live Your agent wires the streams, watches Live Events, and rewrites a function when one of them throws. It runs the fix against a real event before shipping it, so nothing is persisted until it works. Every change lands in the audit log tagged mcp, so you can tell what the agent did from what a person did. It's all MIT licensed, and it runs against your own deployment. Jitsu is one of the fastest growing open-source CDPs with 5,000+ GitHub stars. Capturing events is unlimited and free, and delivery is free up to 200k events a month. Comment Jitsu and I'll DM you the exact prompts I run in Claude Code to build an event pipeline end to end.

Soham Mehta

276,846 views • 7 days ago

there's now a formal proof that your agent's vector memory forgets what you stored and fabricates things you never did. scaling it up makes both worse, not better. "the price of meaning" (arxiv 2603.27116) proves it for any memory that retrieves by similarity in an embedding space. the same geometry that lets embeddings generalize creates competitor mass in every neighborhood. add data and the crowding grows: retention decays toward zero, and false recall can't be tuned out without throwing away true hits. not a bug in your pipeline. the shape of the math. i learned this the expensive way. 500 stored facts, two weeks into a build, a user asks what i know about their job. retrieval hands back four fragments from different weeks: "i love my job," "thinking of quitting," "my manager is supportive," "my manager micromanages." the agent invents a clean synthesis of all four. the user had switched jobs in between. embeddings measure similarity, not truth. the topology angle says stop storing meaning as geometry, store it as structure. navigate an edge in an AST or a graph instead of searching a neighborhood. no crowding, no decay, no false recall. FORGE backs it: plain AST checks catch structural hallucinations at 100% precision (arxiv 2601.19106). here's what the structural pitch skips. the same proof shows pure structure escapes the geometry only by surrendering the connections embeddings find. you trade fabrication for blindness. so i stopped picking a side. what actually ships across thousands of sessions: – extract facts, not transcripts – resolve conflicts on write: archive the old job, mark the new one active – hybrid retrieval: vectors for discovery, graph for precision – decay plus nightly consolidation, so memory keeps what matters and lets the rest go memory is infrastructure, not a feature. that reframe is the whole game. and it's being measured now. WorldMemArena (may 28, arxiv 2605.29341) scores these paradigms head to head, embedding memory against retrieval-augmented against terminal-agent harnesses, across multimodal action-world tasks. the question moved from "does it remember" to "what kind of memory survives scale." full architecture, with the code, here:

there's now a formal proof that your agent's vector memory forgets what you stored and fabricates things you never did. scaling it up makes both worse, not better. "the price of meaning" (arxiv 2603.27116) proves it for any memory that retrieves by similarity in an embedding space. the same geometry that lets embeddings generalize creates competitor mass in every neighborhood. add data and the crowding grows: retention decays toward zero, and false recall can't be tuned out without throwing away true hits. not a bug in your pipeline. the shape of the math. i learned this the expensive way. 500 stored facts, two weeks into a build, a user asks what i know about their job. retrieval hands back four fragments from different weeks: "i love my job," "thinking of quitting," "my manager is supportive," "my manager micromanages." the agent invents a clean synthesis of all four. the user had switched jobs in between. embeddings measure similarity, not truth. the topology angle says stop storing meaning as geometry, store it as structure. navigate an edge in an AST or a graph instead of searching a neighborhood. no crowding, no decay, no false recall. FORGE backs it: plain AST checks catch structural hallucinations at 100% precision (arxiv 2601.19106). here's what the structural pitch skips. the same proof shows pure structure escapes the geometry only by surrendering the connections embeddings find. you trade fabrication for blindness. so i stopped picking a side. what actually ships across thousands of sessions: – extract facts, not transcripts – resolve conflicts on write: archive the old job, mark the new one active – hybrid retrieval: vectors for discovery, graph for precision – decay plus nightly consolidation, so memory keeps what matters and lets the rest go memory is infrastructure, not a feature. that reframe is the whole game. and it's being measured now. WorldMemArena (may 28, arxiv 2605.29341) scores these paradigms head to head, embedding memory against retrieval-augmented against terminal-agent harnesses, across multimodal action-world tasks. the question moved from "does it remember" to "what kind of memory survives scale." full architecture, with the code, here:

Rohit

16,591 views • 3 months ago

Anthropic AI Engineer: "The fastest way to make an agent better isn't a smarter model. It's the right Loop and Graph around it." In 17 minutes he breaks down what agentic engineering looks like at Anthropic, and why it's nothing like what most people imagine. Watch it, then save the full guide on loops and graphs below

Anthropic AI Engineer: "The fastest way to make an agent better isn't a smarter model. It's the right Loop and Graph around it." In 17 minutes he breaks down what agentic engineering looks like at Anthropic, and why it's nothing like what most people imagine. Watch it, then save the full guide on loops and graphs below

CyrilXBT

10,691 views • 22 days ago

300 agents just worked in parallel. the hard part starts when they’re done. The real unlock is the shared context graph. 100 entities already have 4,950 possible pairwise relationships. at 300, that jumps to 44,850. 300 agents → thousands of steps → shared entities → shared relationships → one connected memory layer Every run adds more structure instead of starting from zero. That means the next agent doesn’t just get more data. It gets a better map of how everything connects. That’s the part people are underestimating about multi-agent systems.

300 agents just worked in parallel. the hard part starts when they’re done. The real unlock is the shared context graph. 100 entities already have 4,950 possible pairwise relationships. at 300, that jumps to 44,850. 300 agents → thousands of steps → shared entities → shared relationships → one connected memory layer Every run adds more structure instead of starting from zero. That means the next agent doesn’t just get more data. It gets a better map of how everything connects. That’s the part people are underestimating about multi-agent systems.

Ricker

34,737 views • 29 days ago

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.

300 agents without shared context is just parallelized confusion. All 300 agents are useless if the research dies inside 300 separate documents. the real unlock is what happens after the search. in K3 graph-native setup: 300 agents 140 linked sources 100% traceable claims 9 contradictions surfaced and every new source changes the graph. now imagine that happening across 8–10 active research clusters at once. instead of 300 isolated summaries, you get one shared structure: source → entity → relationship → evidence → contradiction → verification the math gets ugly fast. 100 entities = 4,950 possible pairwise relationships. that’s why “just run more agents” stops being enough. you need a graph that can keep track of what connects to what. full breakdown in the article below.

Ricker

15,089 views • 25 days 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

244,435 views • 2 years 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

300,859 views • 2 months ago

Anthropic's multi-agent researcher just explained how to actually build a graph of Claude agents: "Multi-agent is where fundamentally you have multiple agents or multiple Claudes working at the same time - one parent agent delegates tasks to five sub-agents that can each then work in parallel." the real architecture: parent agent → delegates to sub-agents (as tools) → sub-agents run in parallel → results roll back up the failure mode nobody talks about: "Overbuilt multi-agent systems spend too much time just talking back and forth with each other and not actually making progress on the main task." sound familiar? that's every bloated human org chart too in this 19-minute conversation, an Anthropic researcher lays out the real framework: parent → sub-agents → tools → context protection = the actual shape of a working agent graph

Anthropic's multi-agent researcher just explained how to actually build a graph of Claude agents: "Multi-agent is where fundamentally you have multiple agents or multiple Claudes working at the same time - one parent agent delegates tasks to five sub-agents that can each then work in parallel." the real architecture: parent agent → delegates to sub-agents (as tools) → sub-agents run in parallel → results roll back up the failure mode nobody talks about: "Overbuilt multi-agent systems spend too much time just talking back and forth with each other and not actually making progress on the main task." sound familiar? that's every bloated human org chart too in this 19-minute conversation, an Anthropic researcher lays out the real framework: parent → sub-agents → tools → context protection = the actual shape of a working agent graph

rewind

27,195 views • 1 month ago

1/ Reviewing agent-written code usually comes down to reading a diff and hoping. That is the part of the workflow nobody solved. The models got very good at producing code, and the burden quietly moved to the person who has to decide whether it is safe to merge. You read it, you spot-check it, you run it locally if you have time, and then you approve on instinct. Vorflux goes after that step directly. Every session spins up your whole stack on a real cloud machine. Repos, databases, CI/CD, feature flags, all of it. The actual environment your app runs in, with real services instead of mocks.

1/ Reviewing agent-written code usually comes down to reading a diff and hoping. That is the part of the workflow nobody solved. The models got very good at producing code, and the burden quietly moved to the person who has to decide whether it is safe to merge. You read it, you spot-check it, you run it locally if you have time, and then you approve on instinct. Vorflux goes after that step directly. Every session spins up your whole stack on a real cloud machine. Repos, databases, CI/CD, feature flags, all of it. The actual environment your app runs in, with real services instead of mocks.

Chubby♨️

16,711 views • 28 days ago

Build a loan underwriting agent workflow in ~5 mins 💵🤖 (No code, just English) I built an agentic workflow that can process incoming PDFs of financial statements: checking statements, bank statements, brokerage accounts, and extract/normalize the financials in each source of data. I did this by specifying the schemas and classification logic in plain English; our agent compiles this into a deterministic workflow with calls to agentic parsing to extract out all the information that you need. Our agent builder is now in LlamaCloud, you can sign up and try it yourself! Blog: Sign up:

Build a loan underwriting agent workflow in ~5 mins 💵🤖 (No code, just English) I built an agentic workflow that can process incoming PDFs of financial statements: checking statements, bank statements, brokerage accounts, and extract/normalize the financials in each source of data. I did this by specifying the schemas and classification logic in plain English; our agent compiles this into a deterministic workflow with calls to agentic parsing to extract out all the information that you need. Our agent builder is now in LlamaCloud, you can sign up and try it yourself! Blog: Sign up:

Jerry Liu

30,015 views • 7 months ago