Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I conducted a multi-agent code audit where 48 Claude agents check a repository in parallel Modern automation excels through graph architecture, allowing a network of tailored AI units to tackle intricate problems together Here is how the process works: 48 Claude models inspect distinct segments of the same codebase...

Bober_smart's profile picture

Bober_smart

14,931 subscribers

16,818 görüntüleme • 26 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.
0:18

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,690 görüntüleme • 4 ay önce

It is becoming f*cking dangerous: I don't understand why everyone still isn't doing this, thanks to this I reached an income of $12,000 as early as 3 months ago Andrej Karpathy, co-founder of OpenAI, shared a straightforward concept that blew up with over 23 million views: stop relying on AI strictly for coding and start using it to construct your own personal knowledge engine Point Claude Code to a folder, toss in raw materials (whether it's an article, a video transcript, or a PDF) and Claude processes everything, links relevant topics together, and organizes it into a self-updating wiki of your personal knowledge. It acts like compound interest: the more information you add, the more capable it becomes Here is the exact breakdown: Set up Obsidian, create a fresh vault, and open it using Claude Code Supply Karpathy's wiki layout prompt and instruct Claude to build the architecture Claude automatically sets up three components: a ⁠raw⁠ directory for source files, a ⁠wiki⁠ directory for processed pages, and a ⁠CLAUDE.md⁠ control file to run the system Dump any document into the ⁠raw⁠ folder and run "ingest this" Query your entire knowledge repository at any time, indefinitely It takes just five minutes to configure, eliminating the need to ever start a conversation with a completely blank context window again Check the link below for the complete step-by-step walkthrough on setting up Claude with Obsidian Bookmark this post for later
0:19

It is becoming f*cking dangerous: I don't understand why everyone still isn't doing this, thanks to this I reached an income of $12,000 as early as 3 months ago Andrej Karpathy, co-founder of OpenAI, shared a straightforward concept that blew up with over 23 million views: stop relying on AI strictly for coding and start using it to construct your own personal knowledge engine Point Claude Code to a folder, toss in raw materials (whether it's an article, a video transcript, or a PDF) and Claude processes everything, links relevant topics together, and organizes it into a self-updating wiki of your personal knowledge. It acts like compound interest: the more information you add, the more capable it becomes Here is the exact breakdown: Set up Obsidian, create a fresh vault, and open it using Claude Code Supply Karpathy's wiki layout prompt and instruct Claude to build the architecture Claude automatically sets up three components: a ⁠raw⁠ directory for source files, a ⁠wiki⁠ directory for processed pages, and a ⁠CLAUDE.md⁠ control file to run the system Dump any document into the ⁠raw⁠ folder and run "ingest this" Query your entire knowledge repository at any time, indefinitely It takes just five minutes to configure, eliminating the need to ever start a conversation with a completely blank context window again Check the link below for the complete step-by-step walkthrough on setting up Claude with Obsidian Bookmark this post for later

Bober_smart

82,139 görüntüleme • 9 gün önce

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓
0:15

this is worth more than most five figure courses 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓

Argona

157,688 görüntüleme • 3 ay önce

I launched 300 Grok agents to automate the routine and see what would come of it. As a result, my business reached a profit of +356% Honestly, I still don't understand why absolutely everyone isn't using this method. While everyone else is writing posts and monitoring trends manually, this AI stack works like a well-oiled clockwork mechanism How it's structured: Dedicated cloud instances share the load via a single distributed bus, distributing tasks in batches of 50 parallel threads per agent The central configurator dynamically switches tasks between system workers, processing domains, parsing inputs, and gathering results into a single knowledge graph Each agent runs an algorithm through a fixed cycle (setup -> run -> correct -> save -> schedule), instantly correcting deviations and fixing data in the database Instead of spending hundreds of hours on manual operations, I handed all this machinery over to AI. The result speaks for itself, reach and productivity have grown exponentially, and the system operates autonomously 24/7 The visualization is made for a clear example and may differ from the actual work of the agents The article describes the detailed automation method, bookmark it
0:10

I launched 300 Grok agents to automate the routine and see what would come of it. As a result, my business reached a profit of +356% Honestly, I still don't understand why absolutely everyone isn't using this method. While everyone else is writing posts and monitoring trends manually, this AI stack works like a well-oiled clockwork mechanism How it's structured: Dedicated cloud instances share the load via a single distributed bus, distributing tasks in batches of 50 parallel threads per agent The central configurator dynamically switches tasks between system workers, processing domains, parsing inputs, and gathering results into a single knowledge graph Each agent runs an algorithm through a fixed cycle (setup -> run -> correct -> save -> schedule), instantly correcting deviations and fixing data in the database Instead of spending hundreds of hours on manual operations, I handed all this machinery over to AI. The result speaks for itself, reach and productivity have grown exponentially, and the system operates autonomously 24/7 The visualization is made for a clear example and may differ from the actual work of the agents The article describes the detailed automation method, bookmark it

Bober_smart

14,733 görüntüleme • 2 ay önce

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇
0:15

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇

wast3

18,460 görüntüleme • 2 ay önce

AI coding agents re-explore the same codebase every single session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.
0:17

AI coding agents re-explore the same codebase every single session. Repowise indexes a repo once and gives Claude Code, Codex, or any MCP agent a real dependency graph, git history, and a bug-predictive code health score. No re-grepping the same files. No stale docs. No guessing which file is about to break. The loop is simple: measure every file > locate where the risk concentrates > generate the exact refactoring plan to fix it Indexing a repo takes under 30 seconds and updates automatically on every commit. Paired benchmarks show up to 96% fewer tokens spent loading context and 70% fewer agent tool calls, at the same answer quality.

Simplifying AI

17,561 görüntüleme • 2 ay önce

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks
0:10

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks

Bober_smart

2,883,416 görüntüleme • 2 ay önce

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂
0:18

Advent of Claude Day 31 - Claude Agent SDK I saved the best for last. The same agent loop, tools, and context management that power Claude Code is available as an SDK. Build agents that work like Claude Code in as little as 10 lines of code. This is just the beginning. 🎇🥂

Ado

100,117 görüntüleme • 9 ay önce

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.
0:11

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

Alvaro Cintas

75,596 görüntüleme • 2 ay önce

It is becoming f*cking dangerous: I launched a full-fledged autonomous crawler that parses any website with ZERO LINES OF CODE Forget about Python, terminals, CSS selectors, and constant manual copy-pasting You can set up a seamless No-Code integration just once, where Claude becomes the brain of your automatic data collector, and the results automatically flow straight into your spreadsheets In this setup, a No-Code service accesses the website and grabs the raw content, while Claude instantly cleans out the noise, extracts the key insights, and organizes everything neatly How to set this up: 1. Pick a No-Code service: Sign up for makecom, zapiercom, or install the bardeenai extension (all of them offer free tiers) 2. Set up the Launch: Specify how often the crawler should run (for example, Every day at 9:00 AM or At the click of a button) and feed it the target URLs 3. Connect the Claude module: Add an AI step to your scenario and give Claude a clear instruction: "Analyze the provided page text. Extract product names, prices, discounts, and seller contact details. Return the data as a clean, structured list" 4. Choose where to save the results: Connect the final step (for instance, Google Sheets or Notion) Quick 10-minute setup, full 24/7 autonomy, and zero headache with code maintenance. Essentially, with just a few clicks you are creating your own smart AI agent that quietly handles the routine work while you focus on real tasks Bookmark this for later
0:19

It is becoming f*cking dangerous: I launched a full-fledged autonomous crawler that parses any website with ZERO LINES OF CODE Forget about Python, terminals, CSS selectors, and constant manual copy-pasting You can set up a seamless No-Code integration just once, where Claude becomes the brain of your automatic data collector, and the results automatically flow straight into your spreadsheets In this setup, a No-Code service accesses the website and grabs the raw content, while Claude instantly cleans out the noise, extracts the key insights, and organizes everything neatly How to set this up: 1. Pick a No-Code service: Sign up for makecom, zapiercom, or install the bardeenai extension (all of them offer free tiers) 2. Set up the Launch: Specify how often the crawler should run (for example, Every day at 9:00 AM or At the click of a button) and feed it the target URLs 3. Connect the Claude module: Add an AI step to your scenario and give Claude a clear instruction: "Analyze the provided page text. Extract product names, prices, discounts, and seller contact details. Return the data as a clean, structured list" 4. Choose where to save the results: Connect the final step (for instance, Google Sheets or Notion) Quick 10-minute setup, full 24/7 autonomy, and zero headache with code maintenance. Essentially, with just a few clicks you are creating your own smart AI agent that quietly handles the routine work while you focus on real tasks Bookmark this for later

Bober_smart

26,585 görüntüleme • 9 gün önce

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.
0:16

New open-source agent harness just landed! I got early access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.

elvis

11,303 görüntüleme • 2 ay önce

Claude Code Agent Teams are f*cking ridiculous 🤯 One prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)
0:10

Claude Code Agent Teams are f*cking ridiculous 🤯 One prompt → a team lead breaks your project into pieces, spins up multiple AI agents, and they all work on different parts simultaneously. Research, builds, reviews, and debugging: all happening at the same time. All inside Claude Code. If you're running complex projects where every step waits on the last one... Agent teams eliminate the entire bottleneck: → Tell Claude what you need and describe the team structure in plain English → A lead agent breaks the work into a shared task list → It spawns 3-5 teammates — each with their own context and workspace → Teammates research, build, test, and review in parallel → They message each other, share findings, and challenge each other's work → The lead synthesizes everything into a finished deliverable No managing agents yourself. No waiting for step 1 to finish before step 2 starts. No single-lens reviews that miss half the issues. What you get: → Competitive research across 5 brands done in minutes instead of hours → Multi-component builds where frontend, backend, and data layers happen simultaneously → Creative reviews from 3 different angles at once — brand voice, conversion, differentiation → Funnel debugging where 4 agents investigate 4 theories and debate until they find the real answer Built 100% in Claude Code with one settings change. I put together a full DTC playbook: 5 workflows with copy-paste prompts, the exact setup process, token management tips, and honest guidance on when agent teams are worth it vs. when a simpler approach is the better move. Want it for free? > Like this post > Comment "AGENTS" And I'll send it over (must be following so I can DM)

Mike Futia

46,537 görüntüleme • 7 ay önce

I just built a complete SEO audit plugin in Claude Code that replaces your $200/mo Ahrefs subscription 🤯 One Claude Plugin audits any store: technical SEO, product schema, content, Core Web Vitals, and AI-search readiness. Parallel agents, a 0-100 score, and a dashboard that renders right in the panel. All inside Claude Code. So I pointed it at Ridge .com, one of the sharpest DTC operators out there. It came back 56/100, and what stood out wasn't a knock on them at all: Ridge has a better AI-commerce setup than 99% of stores. A real llms.txt, an agent-discovery sitemap, a live MCP endpoint, genuinely ahead of the curve. And even on a store that dialed-in, the audit surfaced fixable gaps in ~90 seconds: → Room to add product structured data → A mobile Core Web Vitals score worth tightening → A thin meta description on a high-traffic collection Perfect for e-comm operators and SEO agencies who are sick of paying $200/mo for tools that bury the real issues, running quarterly audits that take a week, and shipping reports nobody can act on. So I put together the full playbook to build your own. The complete guide to building this Plugin in Claude Code: branded to you, tuned to exactly how you audit, repeatable across every client. The kind of audit you run in minutes and hand over as a deliverable that looks like it cost thousands. What's inside: → The architecture (orchestrator + parallel sub-agents) → How to fetch any store past Cloudflare → The 0-100 scoring + falsifiable-findings framework → How to ship the HTML dashboard for client demos → The full build, start to finish Want the playbook for free? > Like this post > Comment "SEO" And I'll send it over (must be following so I can DM)
0:17

I just built a complete SEO audit plugin in Claude Code that replaces your $200/mo Ahrefs subscription 🤯 One Claude Plugin audits any store: technical SEO, product schema, content, Core Web Vitals, and AI-search readiness. Parallel agents, a 0-100 score, and a dashboard that renders right in the panel. All inside Claude Code. So I pointed it at Ridge .com, one of the sharpest DTC operators out there. It came back 56/100, and what stood out wasn't a knock on them at all: Ridge has a better AI-commerce setup than 99% of stores. A real llms.txt, an agent-discovery sitemap, a live MCP endpoint, genuinely ahead of the curve. And even on a store that dialed-in, the audit surfaced fixable gaps in ~90 seconds: → Room to add product structured data → A mobile Core Web Vitals score worth tightening → A thin meta description on a high-traffic collection Perfect for e-comm operators and SEO agencies who are sick of paying $200/mo for tools that bury the real issues, running quarterly audits that take a week, and shipping reports nobody can act on. So I put together the full playbook to build your own. The complete guide to building this Plugin in Claude Code: branded to you, tuned to exactly how you audit, repeatable across every client. The kind of audit you run in minutes and hand over as a deliverable that looks like it cost thousands. What's inside: → The architecture (orchestrator + parallel sub-agents) → How to fetch any store past Cloudflare → The 0-100 scoring + falsifiable-findings framework → How to ship the HTML dashboard for client demos → The full build, start to finish Want the playbook for free? > Like this post > Comment "SEO" And I'll send it over (must be following so I can DM)

Mike Futia

55,905 görüntüleme • 4 ay önce

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:
0:19

A massive repository with end-to-end examples of AI applications with React! Together with MCP and A2A, the Agent-User Interaction Protocol (AG-UI) is the third piece that will help you build user-facing AI agents. This GitHub repository will give you access to a bunch of examples showing you how to build the following: • Real-time updates between AI and users • Shared mutable state between agents and users • Tool orchestration • Security boundaries • UI synchronization In every one of these examples, you'll get the following: • Client sends a POST request to the agent endpoint • Then listens to a unified event stream over HTTP • Each event includes a type and a minimal payload • Agents emit events in real-time • The frontend can react immediately to these events • The frontend emits events and context back to the agent Check the link in the next post:

Santiago

78,271 görüntüleme • 1 yıl önce

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.
0:18

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.

Radha Tripathi

23,136 görüntüleme • 5 ay önce

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.
0:10

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAI’s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAI’s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agent—from visual design to deployment and performance tuning—inside a single unified system.

Rohan Paul

178,460 görüntüleme • 1 yıl önce

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.
0:17

Another WTF moment. A developer just open-sourced a coding agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.

Brady Long

209,050 görüntüleme • 2 ay önce

launched a drone swarm where each drone is a Grok agent, and 8 days later, my profit reached $8,765 I delegated the management of the trading terminal to an autonomous structure consisting of 8 core Grok agents and 54 auxiliary drone agents. The latter constantly scan the network, gather raw data, and instantly redirect it to the main 8 While the morning sync meeting takes place at 6 AM, which I don't even attend, the system is already hard at work Hierarchy and responsibilities of the key agents: HEAD OF DESK: The brain of the operation. Never makes trades himself, but filters data streams, checks transmission quality, and issues a final verdict requiring manual approval SEARCH: Hunts for actual alpha, studies fresh commits in GitHub repositories, and tracks hidden Telegram signals before anyone else notices them RISK: Conducts smart contract audits, checks minting functions and liquidity pool (LP) lock functions, filtering out scams and honeypots even before entry SNIPER: Responsible for execution (instantly sends high-speed on-chain orders at the exact millisecond the risk check is completed) WHALE: Hunts "smart money" wallets, tracking large insider purchases in real-time RUG: Monitors developer activity around the clock and instantly dumps assets if they try to pull liquidity (LP) EXIT: Manages the dynamic trailing stop, withdrawing capital step-by-step as market liquidity grows SHILL: Analyzes social noise, impulse intensity, and key calls from top influencers All of this huge routine work of collecting information and delivering it to the core agents is provided by those very 54 drone agents operating in the background While I was sleeping, the autonomous complex managed to analyze 187 tokens, selected the 27 most promising configurations, and closed 8 successful trades. The net profit was $8,765 Each agent operates in an isolated environment: it has its own virtual browser, terminal, and local cloud memory. The trading floor operates 24/7, even when my laptop is completely turned off How to deploy such a system in one evening: 1. Launch the Grok Bot and set up the main agent (Head of Desk) 2. Distribute roles among the other 7 agents, writing out tasks for them in plain human language, as if you were hiring live interns 3. Run the starting workflow on your screen, allowing them to adopt the algorithm of actions 4. Integrate alerts into Telegram and connect wallets via webhooks No complicated VPS setups, writing lines of code, or tedious waiting for developers. Forget about 16 hours in front of the monitor, buying expensive private chats, and burnout (it took me just one evening to fully automate the process) Add this to your bookmarks, you will need these settings before your next trade
0:20

launched a drone swarm where each drone is a Grok agent, and 8 days later, my profit reached $8,765 I delegated the management of the trading terminal to an autonomous structure consisting of 8 core Grok agents and 54 auxiliary drone agents. The latter constantly scan the network, gather raw data, and instantly redirect it to the main 8 While the morning sync meeting takes place at 6 AM, which I don't even attend, the system is already hard at work Hierarchy and responsibilities of the key agents: HEAD OF DESK: The brain of the operation. Never makes trades himself, but filters data streams, checks transmission quality, and issues a final verdict requiring manual approval SEARCH: Hunts for actual alpha, studies fresh commits in GitHub repositories, and tracks hidden Telegram signals before anyone else notices them RISK: Conducts smart contract audits, checks minting functions and liquidity pool (LP) lock functions, filtering out scams and honeypots even before entry SNIPER: Responsible for execution (instantly sends high-speed on-chain orders at the exact millisecond the risk check is completed) WHALE: Hunts "smart money" wallets, tracking large insider purchases in real-time RUG: Monitors developer activity around the clock and instantly dumps assets if they try to pull liquidity (LP) EXIT: Manages the dynamic trailing stop, withdrawing capital step-by-step as market liquidity grows SHILL: Analyzes social noise, impulse intensity, and key calls from top influencers All of this huge routine work of collecting information and delivering it to the core agents is provided by those very 54 drone agents operating in the background While I was sleeping, the autonomous complex managed to analyze 187 tokens, selected the 27 most promising configurations, and closed 8 successful trades. The net profit was $8,765 Each agent operates in an isolated environment: it has its own virtual browser, terminal, and local cloud memory. The trading floor operates 24/7, even when my laptop is completely turned off How to deploy such a system in one evening: 1. Launch the Grok Bot and set up the main agent (Head of Desk) 2. Distribute roles among the other 7 agents, writing out tasks for them in plain human language, as if you were hiring live interns 3. Run the starting workflow on your screen, allowing them to adopt the algorithm of actions 4. Integrate alerts into Telegram and connect wallets via webhooks No complicated VPS setups, writing lines of code, or tedious waiting for developers. Forget about 16 hours in front of the monitor, buying expensive private chats, and burnout (it took me just one evening to fully automate the process) Add this to your bookmarks, you will need these settings before your next trade

Bober_smart

30,834 görüntüleme • 1 ay önce

CLAUDE CODE SKILL THAT DESIGNS LOGOS AS PURE CODE The constraint that forced the whole approach: Claude Code has no access to image generation So instead of faking it, one developer built a skill that writes the logo as SVG - actual XML - and renders that to a PNG The process runs in four phases: interview [ reads your repo first, asks about brand and audience only for what it can’t already see ] explore [ dispatches parallel agents that generate 3-5 distinct SVG concepts at once, shown side by side in an HTML preview with a light/dark toggle ] refine, export at 7 standard sizes from favicon to 2048px Because it’s real SVG and not a rasterized image, nothing about it degrades - same file works as a 16px favicon and a 2048px app icon, and every version is hand editable code afterward if you want to nudge one curve The creator’s own account of using it: roughly 15 rounds of generate, curate, cull, repeat - some concepts literally spelled out the product name, others went fully abstract, treating the whole thing like an evolutionary design process instead of a single lucky prompt The part worth remembering before you reach for a paid AI logo tool: this whole approach exists specifically because Claude Code can’t generate images - the constraint produced a better artifact than the workaround usually does full below
0:12

CLAUDE CODE SKILL THAT DESIGNS LOGOS AS PURE CODE The constraint that forced the whole approach: Claude Code has no access to image generation So instead of faking it, one developer built a skill that writes the logo as SVG - actual XML - and renders that to a PNG The process runs in four phases: interview [ reads your repo first, asks about brand and audience only for what it can’t already see ] explore [ dispatches parallel agents that generate 3-5 distinct SVG concepts at once, shown side by side in an HTML preview with a light/dark toggle ] refine, export at 7 standard sizes from favicon to 2048px Because it’s real SVG and not a rasterized image, nothing about it degrades - same file works as a 16px favicon and a 2048px app icon, and every version is hand editable code afterward if you want to nudge one curve The creator’s own account of using it: roughly 15 rounds of generate, curate, cull, repeat - some concepts literally spelled out the product name, others went fully abstract, treating the whole thing like an evolutionary design process instead of a single lucky prompt The part worth remembering before you reach for a paid AI logo tool: this whole approach exists specifically because Claude Code can’t generate images - the constraint produced a better artifact than the workaround usually does full below

YARD

10,875 görüntüleme • 1 ay önce

It blows my mind how few people have implemented this setup. A year ago, this exact system allowed me to automate 90% of my tasks and expand my business Andrey Karpathy, co-founder of OpenAI, dropped a simple idea that generated 22 million views and 108,000 saves "stop relying on AI strictly for generating code, and start leveraging it to build a personal second brain" The logic is straightforward: You link Claude Code to a specific directory and throw in any reference materials (articles, meeting transcripts, or PDFs) The system analyzes the text, maps out connections, and constructs a living repository of everything you know. It compounds continuously: as you feed it more data, the entire ecosystem becomes significantly smarter How it breaks down in practice: Launch Obsidian, set up a new repository, and connect it to Claude Code Feed in the template based on Karpathy's wiki approach and instruct Claude to deploy the architecture The model automatically constructs three core areas: raw for your incoming documents, wiki for organized pages, and a master CLAUDE file that coordinates all processes Move any new resource into the raw folder and issue a quick command to process it Query your entire personal knowledge base whenever you need answers A quick five-minute deployment means you will never have to initiate a prompt from a blank canvas again I published the complete guide in the article. Make sure to bookmark it for later
0:12

It blows my mind how few people have implemented this setup. A year ago, this exact system allowed me to automate 90% of my tasks and expand my business Andrey Karpathy, co-founder of OpenAI, dropped a simple idea that generated 22 million views and 108,000 saves "stop relying on AI strictly for generating code, and start leveraging it to build a personal second brain" The logic is straightforward: You link Claude Code to a specific directory and throw in any reference materials (articles, meeting transcripts, or PDFs) The system analyzes the text, maps out connections, and constructs a living repository of everything you know. It compounds continuously: as you feed it more data, the entire ecosystem becomes significantly smarter How it breaks down in practice: Launch Obsidian, set up a new repository, and connect it to Claude Code Feed in the template based on Karpathy's wiki approach and instruct Claude to deploy the architecture The model automatically constructs three core areas: raw for your incoming documents, wiki for organized pages, and a master CLAUDE file that coordinates all processes Move any new resource into the raw folder and issue a quick command to process it Query your entire personal knowledge base whenever you need answers A quick five-minute deployment means you will never have to initiate a prompt from a blank canvas again I published the complete guide in the article. Make sure to bookmark it for later

Bober_smart

111,221 görüntüleme • 25 gün önce