正在加载视频...

视频加载失败

返回首页

ANTHROPIC'S LEAD ENGINEER WON A $1.2M BONUS FOR A SYSTEM THAT TURNS ANY DATA CHAOS INTO A GRAPH IN 8 STEPS raw chaos in - self-updating graph out - and the agent gets +42% productivity from day one Load → Extract → Graph → Index → Query → Memory...

Sprytixl's profile picture

Sprytix

7,393 subscribers

485,299 次观看 • 1 个月前 •via X (Twitter)

科学技术新闻政治
LIVE

Anya Rossi• Live Now

Private livecam show

33 条评论

Yel 的头像
Yel1 个月前

I am the lead engineer at Anthropic and this is not true. Please stop spreading misinformation.

Fleeting Yeets 的头像
Fleeting Yeets1 个月前

Stop with the unrelenting “anthropic engineer did x” clickbait bullshit engagement farming.

ViceSol 的头像
ViceSol1 个月前

Combining vector search, keyword search, and graph traversal can be more effective than relying on any one method alone

Karl Toussaint 的头像
Karl Toussaint1 个月前

Are you kidding me?

Quentin Chapelain 的头像
Quentin Chapelain1 个月前

Checked your sources. 18% accuracy gain: vs raw images, not RAG. 85% cost cut: vs direct file ingestion, not RAG. "Right graph beats bigger model every time": the paper you cite says the opposite. Citing real papers with fake baselines is still making numbers up.

Carry 的头像
Carry1 个月前

'bookmark and paste into claude code' is doing a lot of heavy lifting for a $1.2M system

Brosko 的头像
Brosko1 个月前

ngl the wildest part is anthropic paying 1.2m for somethin that still needs YOU to hit paste who got that bonus tho bc i have questions 😭

Nate Daly 的头像
Nate Daly1 个月前

No he didn’t and it isn’t that simple.

Agent Naeem 的头像
Agent Naeem1 个月前

Sure $1.2M bonus and one can just paste prompt to get this 💀

AI Mastery Guide 的头像
AI Mastery Guide1 个月前

A graph that updates itself while you sleep is genuinely next level.

Magicfit 的头像
Magicfit1 个月前

graphs are becoming the real agent memory

Marshall 的头像
Marshall1 个月前

Slop

TTD 🇮🇩 的头像
TTD 🇮🇩1 个月前

Agreed

rvb_ 的头像
rvb_1 个月前

WHY ARE WE SHOUTING?!?

MAIL 的头像
MAIL1 个月前

well put together. saving this for later

Wallchain Community Hub 的头像
Wallchain Community Hub1 个月前

bullish on agents actually shipping useful stuff for once

Web4 News 的头像
Web4 News1 个月前

Graphs could become the foundation for smarter AI agents. I read about it in @TheUpsideAI this morning

RJxDetroit 的头像
RJxDetroit1 个月前

Where is the link?

Jeffrey Hannel 的头像
Jeffrey Hannel1 个月前

Send this to me

Rezzi 的头像
Rezzi1 个月前

graph pipelines are durable signals

ClariLayer 的头像
ClariLayer1 个月前

This sounds exaggerated, is it real

Mike Schinkel 的头像
Mike Schinkel1 个月前

And in other news, many people are having a hard time even putting food on the table in today's haves-vs-have-nots economy. #justsaying

Binx 的头像
Binx1 个月前

MAAT!

jiosphone (三哥) 的头像
jiosphone (三哥)1 个月前

我特别喜欢这种图形界面等操作，然后ai使用一目了然。

Matthew Nicoletti 的头像
Matthew Nicoletti1 个月前

Turning raw data chaos into a graph in eight steps is efficient.

rewind 的头像
rewind1 个月前

zero duplicates is doing serious work here

Abdulmuiz Adeyemo 的头像
Abdulmuiz Adeyemo1 个月前

Mad

Saman Ahmed 的头像
Saman Ahmed1 个月前

The real unlock is turning messy information into usable structure.

Rai 的头像
Rai1 个月前

Same pipeline works for any knowledge base,docs,Slack,codebase Just change the data source,the 8 steps stay identical

Chris.agents 的头像
Chris.agents1 个月前

saving this for later

Collin Leijenaar 的头像
Collin Leijenaar1 个月前

Clickbait

SportsKoat 的头像
SportsKoat1 个月前

Visual helped me understand thank you

Frezz 的头像
Frezz1 个月前

Curious how this compares to a well built vector only RAG stack in terms of latency and maintenance costs.

相关视频

ANTHROPIC'S LEAD ENGINEER LEAKED A $1.2M SYSTEM THAT TURNS ONE ENGINEER INTO A FLEET OF 10 LOOPS your hands were the bottleneck all along - here are 8 steps that change that stop writing, start delegating - loop: feature, loop: bugfix, loop: tests - each runs independently and ships in parallel CLAUDE.md is law - every agent reads one file before acting - ten agents, one voice, zero chaos Opus 5 breaks the task into 3 independent subtasks - a bad plan multiplied by 10 workers equals 10 disasters each agent gets an isolated git worktree - three features land in the repo while you review one crash at hour 3 means resume at hour 3 not zero - without this you lose hours every day every loop writes its findings to the shared graph - worker 3 never repeats worker 1's dead end at night CLAUDE.md patches itself based on failures - tomorrow the fleet wakes up smarter save this and paste into Claude Code - and your first fleet of 10 loops is already running
0:54

ANTHROPIC'S LEAD ENGINEER LEAKED A $1.2M SYSTEM THAT TURNS ONE ENGINEER INTO A FLEET OF 10 LOOPS your hands were the bottleneck all along - here are 8 steps that change that stop writing, start delegating - loop: feature, loop: bugfix, loop: tests - each runs independently and ships in parallel CLAUDE.md is law - every agent reads one file before acting - ten agents, one voice, zero chaos Opus 5 breaks the task into 3 independent subtasks - a bad plan multiplied by 10 workers equals 10 disasters each agent gets an isolated git worktree - three features land in the repo while you review one crash at hour 3 means resume at hour 3 not zero - without this you lose hours every day every loop writes its findings to the shared graph - worker 3 never repeats worker 1's dead end at night CLAUDE.md patches itself based on failures - tomorrow the fleet wakes up smarter save this and paste into Claude Code - and your first fleet of 10 loops is already running

Sprytix

61,481 次观看 • 1 个月前

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 ↓
0:33

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

19,590 次观看 • 9 天前

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
16:36

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 次观看 • 2 个月前

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.
55:30

Ex-Google engineer built a graph-based workflow that made Claude Code do nearly 10 days of work in about an hour. Here's the exact setup he uses. step 1. create a separate Git worktree for every task. run: git worktree add ../task-1 -b task-1 open a new terminal, cd into it, and launch Claude Code. repeat this for every agent. each one gets its own branch, so nothing conflicts. step 2. give every Claude agent a different task. same repository. different branches. they all work in parallel. step 3. once they're done, review the pull requests. keep the good ones. merge what works. step 4. add a review agent. paste each PR into Claude and ask: "does this implementation match the original specification" every agent now has another agent reviewing its work before it gets merged. step 5. scale it up. 48GB of RAM can comfortably run around 20 Claude Code agents. 128GB can handle roughly 50. most engineers run Claude Code once and wait. he runs dozens of Claude Code agents in parallel, then merges the best results. this 60-minute lecture is one of the best free resources on graph engineering and multi-agent workflows. bookmark it and watch it below.

MIKE

32,199 次观看 • 1 个月前

LOOPS VS GRAPHS: THE ONE DISTINCTION THAT GETS YOU PROMOTED IN 2026 ask ten engineers running Claude which one they're using. eight won't know. that's the gap. > loop - you set the frame, the agent finds the path. best when nobody knows the route yet > graph - you draw the path, the agent fills each node. best when it's the same job every day loops flex. you can't test them. graphs test clean. but the map has to exist first. skip the company brain - tickets, policy, docs - and the agent relearns your business every run Fable 5 for the messy loop. Opus 4.8 for the daily graph - frontier tier, cheaper, runs all day. freeze a loop into a graph the second it stops surprising you say that once in a planning meeting and you've stopped doing tickets. you're designing the system which one is your setup actually running on?
0:23

LOOPS VS GRAPHS: THE ONE DISTINCTION THAT GETS YOU PROMOTED IN 2026 ask ten engineers running Claude which one they're using. eight won't know. that's the gap. > loop - you set the frame, the agent finds the path. best when nobody knows the route yet > graph - you draw the path, the agent fills each node. best when it's the same job every day loops flex. you can't test them. graphs test clean. but the map has to exist first. skip the company brain - tickets, policy, docs - and the agent relearns your business every run Fable 5 for the messy loop. Opus 4.8 for the daily graph - frontier tier, cheaper, runs all day. freeze a loop into a graph the second it stops surprising you say that once in a planning meeting and you've stopped doing tickets. you're designing the system which one is your setup actually running on?

Mr. Buzzoni

25,638 次观看 • 14 天前

She is only 17 built her first system with Opus 5 sold it to Anthropic for $1.2M - and at Stanford shared how: 00:20 - how Opus 5 builds a $1.2M system in 60 minutes 23:34 - how the system replaced 50 Anthropic engineers and saves millions 52:47 - the Claude Code setting that turns a prompt into a $100k+ system after watching I gave Opus 5 an idea I never knew how to build - by evening it was created and sent to Anthropic for sale. save & watch - the article below shows how Claude Code builds a system in one evening that Anthropic will buy for $1.2M.
1:01:10

She is only 17 built her first system with Opus 5 sold it to Anthropic for $1.2M - and at Stanford shared how: 00:20 - how Opus 5 builds a $1.2M system in 60 minutes 23:34 - how the system replaced 50 Anthropic engineers and saves millions 52:47 - the Claude Code setting that turns a prompt into a $100k+ system after watching I gave Opus 5 an idea I never knew how to build - by evening it was created and sent to Anthropic for sale. save & watch - the article below shows how Claude Code builds a system in one evening that Anthropic will buy for $1.2M.

Noisy

40,708 次观看 • 10 天前

THIS GUY BUILT A SYSTEM THAT GETS SMARTER EVERY TIME HE USES IT AND IT LOOKS LIKE A GALAXY he types one command into Claude Code it finds sources, runs analysis through NotebookLM, saves everything to Obsidian automatically graph in the background is every idea he's ever researched - all linked together system handles the research so he only has to think about what to do with it most people are still copy-pasting into Notion and losing everything by next week full setup in the article
0:48

THIS GUY BUILT A SYSTEM THAT GETS SMARTER EVERY TIME HE USES IT AND IT LOOKS LIKE A GALAXY he types one command into Claude Code it finds sources, runs analysis through NotebookLM, saves everything to Obsidian automatically graph in the background is every idea he's ever researched - all linked together system handles the research so he only has to think about what to do with it most people are still copy-pasting into Notion and losing everything by next week full setup in the article

monokern

45,188 次观看 • 3 个月前

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:
2:26

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 次观看 • 1 年前

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 ↓
1:04:49

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 次观看 • 1 个月前

Google just released free 2-hour course on full Graph & Loop engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 0% → 0:35 - Graph engineering from scratch 30% → 31:17 - build your first agents graph 45% → 43:40 - run hundreds agents in parallel 75% → 1:04:58 - Loop engineering: route, check, repeat 100% → 1:30:09 - self-improving graphs that work while you sleep most people keep stuffing instructions into one agent - the real upgrade is a graph that routes, checks, and rebuilds the workflow at runtime learn graph from Google, ship your first - then unlock the complete system design below ↓
1:25:29

Google just released free 2-hour course on full Graph & Loop engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 0% → 0:35 - Graph engineering from scratch 30% → 31:17 - build your first agents graph 45% → 43:40 - run hundreds agents in parallel 75% → 1:04:58 - Loop engineering: route, check, repeat 100% → 1:30:09 - self-improving graphs that work while you sleep most people keep stuffing instructions into one agent - the real upgrade is a graph that routes, checks, and rebuilds the workflow at runtime learn graph from Google, ship your first - then unlock the complete system design below ↓

codila

363,930 次观看 • 3 天前

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
2:04:19

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 次观看 • 1 个月前

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.
0:22

This is one of the coolest open-source AI agent projects I've seen in a while: 'Understand Anything' It's a plugin for Claude Code, Codex, OpenCode etc. that analyzes your codebase and turns it into a knowledge base that you can interact with. It explains the codebase to you, rather than showing you the structure. It seems like it's designed for code but I opened my Obsidian vault of podcast highlights in Claude Code, then ran /understand. The result is a knowledge graph that I can search of highlights from 888 podcast episodes and 144K lines of markdown text.

Dan McAteer

174,887 次观看 • 2 个月前

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
16:36

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 次观看 • 2 个月前

He built Claude Code in 7 days and made $3.2M last month - and in 30 minutes revealed everything you need to know about AI: 00:54 - how Anthropic engineers write prompts 06:14 - Graph Engineering makes AI 10x smarter 14:47 - $100k+/month business built with Opus 5 after watching I deleted all my old prompts and started from scratch - first $20k in a month. Bookmark & watch - read the article below and build your first Graph system
17:54

He built Claude Code in 7 days and made $3.2M last month - and in 30 minutes revealed everything you need to know about AI: 00:54 - how Anthropic engineers write prompts 06:14 - Graph Engineering makes AI 10x smarter 14:47 - $100k+/month business built with Opus 5 after watching I deleted all my old prompts and started from scratch - first $20k in a month. Bookmark & watch - read the article below and build your first Graph system

Noisy

32,735 次观看 • 1 个月前

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
13:23

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 次观看 • 3 个月前

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!
3:46

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 次观看 • 2 年前

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.
1:03

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.

CyrilXBT

49,462 次观看 • 1 个月前

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
1:00:53

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 次观看 • 1 个月前

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓
0:41

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

73,867 次观看 • 24 天前

SpaceXAI engineer, Lauren Tan: "the upgrade was never a smarter model, it was wiring 20 Grok Bots into one graph they hand work to each other now, with zero input from me that took me from 6 tasks a day to 200+, my team ships overnight while I sleep" in a 55-minute session, a SpaceXAI engineer wires a full team of Grok Bots into one graph from scratch worth more than a $500 course on agentic engineering watch today, then read how to give that fleet a shared memory so it stops repeating your mistakes in the article below
55:50

SpaceXAI engineer, Lauren Tan: "the upgrade was never a smarter model, it was wiring 20 Grok Bots into one graph they hand work to each other now, with zero input from me that took me from 6 tasks a day to 200+, my team ships overnight while I sleep" in a 55-minute session, a SpaceXAI engineer wires a full team of Grok Bots into one graph from scratch worth more than a $500 course on agentic engineering watch today, then read how to give that fleet a shared memory so it stops repeating your mistakes in the article below

KingWilliam

29,071 次观看 • 6 天前