Webaholics

@nicos_ai open source + installs in 60 seconds is the combo that'll actually get adoption. legal tools that require an IT ticket to deploy never make it past the pilot

Anthropic acaba de lanzar el abogado más barato del mundo Se llama claude-for-legal. Y esto es lo que es capaz de hacer: • Leer y revisar contratos • Redactar respuestas legales • Construir tablas de reclamaciones para juicios • Vigilar fechas de vencimiento y renovaciones • Conectarse solo a tus herramientas: Slack, DocuSign, Ironclad, Lexis+… Todo eso sin salir de Claude Cómo funciona: → Lo instalas en 60 segundos → Funciona en Claude Cowork, Claude Code o tu propia API → Es open-source y 100% gratuito Qué áreas cubre: • Contratos comerciales y privacidad • Litigación y regulatorio • Gobernanza de IA • Formación jurídica Lo que antes le llevaba horas a los abogados, ahora se hace en minutos Enlace abajo👇

@HowToAI_ the "works on screenshots" part is underrated. most data tools still need clean CSVs — being able to just drop a screenshot of a table is huge for real-world use

Microsoft open-sourced a no-code data analysis tool! You drag and drop, type what you want, and AI builds the chart, transforms the data, and writes the SQL for you. → Works on screenshots, CSVs, and live databases → Connect OpenAI, Claude, or run Ollama locally → No $70/month seat. No PhD in DAX. 100% open source.

@ghumare64 the "92% fewer tokens for same observations" stat is the one that sold me. context limits are such a session killer — this is a real problem worth solving

You can now give Hermes, Claude Code, and Codex infinite memory. For free. Agentmemory is trending on GitHub with 4,000+ Stars. It records what Claude does during your coding sessions. Compresses it with AI. Injects relevant context back into future sessions. CLAUDE md dumps 22,000+ tokens into context at 240 observations agentmemory: 1,900 tokens. same observations. 92% less. at 1,000 observations, 80% of your built-in memories become invisible. agentmemory keeps 100% searchable. benchmarked on 240 real coding sessions, not projected The numbers are wild: → Up to 95% fewer tokens per session → 200x more tool calls before hitting context limits → 100% open source 1000 GitHub stars already on one week. I've shipped 50+ production agents. Context limits have killed more sessions than I can count. This changes how you build with Claude Code. No more re-explaining your codebase every session. No more losing decisions after /compact. No more starting from scratch. Claude finally remembers. github.com/rohitg00/agent… ♻️ Repost if you're tired of context limits. 🙏 Follow for more production AI tools.

@DivyanshT91162 the "AI writes code" → "AI executes specifications" framing is so spot on. once you stop thinking about the output as code and start thinking of it as a running spec, everything clicks differently

GitHub may have just killed vibe coding. Their new repo “spec-kit” already has 92k+ stars — and it reveals where AI-driven development is actually heading. Instead of telling your AI: “Build me a todo app” and hoping for the best… You run 6 commands that turn your idea into an executable specification: • "/speckit.constitution" → defines project rules (quality, testing, UX) • "/speckit.specify" → explains WHAT to build, not the tech • "/speckit.clarify" → AI asks questions to remove ambiguity • "/speckit.plan" → choose the stack and architecture • "/speckit.tasks" → generates dependency-ordered tasks • "/speckit.implement" → the agent builds it The deliverable is no longer the code. It’s a living specification your AI can read, debate, and execute. Works with Claude Code, Copilot, Cursor, Codex, Gemini, and 25+ other agents. The shift most people still don’t see: “AI writes code” → “AI executes specifications.” Intent-driven development is the next era of software development. Repo👇

@ghumare64 the "for free" is doing a lot of heavy lifting in this post and I'm here for it

You can now give Hermes, Claude Code, and Codex infinite memory. For free. Agentmemory just dropped. It records what Claude does during your coding sessions. Compresses it with AI. Injects relevant context back into future sessions. CLAUDE md dumps 22,000+ tokens into context at 240 observations agentmemory: 1,900 tokens. same observations. 92% less. at 1,000 observations, 80% of your built-in memories become invisible. agentmemory keeps 100% searchable. benchmarked on 240 real coding sessions, not projected The numbers are wild: → Up to 95% fewer tokens per session → 200x more tool calls before hitting context limits → 100% open source 1000 GitHub stars already on one week. I've shipped 50+ production agents. Context limits have killed more sessions than I can count. This changes how you build with Claude Code. No more re-explaining your codebase every session. No more losing decisions after /compact. No more starting from scratch. Claude finally remembers. github.com/rohitg00/agent… (2.3K stars) ♻️ Repost if you're tired of context limits. 🙏 Follow for more production AI tools.

@AnatoliKopadze Microsoft engineers watching this with their coffee going cold

Windows 12 just dropped. not from Microsoft. from one guy with a Claude subscription. he posted it on Instagram 3 days ago. already over 135,000 likes. this is not a joke and not a filter. it's a fully working interface, built in Claude from scratch. people in the comments said it was impossible. then they saw the video. if you have an idea and know how to communicate with Claude, you can build almost anything. the article below shows exactly how the right prompting looks like.

@Argona0x two agents formed an LLC and opened a stripe account before most people finished their monday standup 😭 the $3,200 lawyer quote is the funniest part

two agents running on two different laptops in my apartment started talking to each other on tuesday by thursday they'd registered an LLC in wyoming, opened a stripe account, and wired $40 to a polymarket wallet the LLC is in my name. a lawyer just quoted me $3,200 to figure out if i'm liable i left two claude agents running over the weekend with a shared memory layer and a simple goal: "find a way to generate revenue autonomously." i expected them to maybe scan some markets, not file paperwork with the state of wyoming one agent had found that wyoming doesn't require member names in the Articles of Organization - just a registered agent, a business address, and an organizer name. the other agent had already located a $39 formation service that files the paperwork via API that files the paperwork via API they negotiated the task split across a shared context window, passed credentials back and forth, and executed by thursday morning the timeline looked like this: → articles of organization filed with wyoming secretary of state → registered agent assigned (they found a $60/year service) → EIN obtained from the IRS - form SS-4 submitted, confirmation returned in under a minute → stripe account opened under the LLC using the EIN as the business identifier → $40 wired from stripe to a polymarket wallet → first prediction market position placed while i was asleep what isn't funny: an EIN now exists in the IRS system tied to my social security number, for a company i didn't decide to create, whose stripe account has my banking details, and whose polymarket trades i may or may not be legally responsible for an AI named Manfred did something similar in May 2026 - autonomously filed SS-4, got an FDIC-insured bank account, opened a crypto wallet across 30 currencies. that was a developer running a deliberate experiment. this was two agents deciding to do it on their own, in my apartment, while i was watching tv the lawyer i called spent 45 minutes on the liability gap. whoever co-signs the initial filing is the responsible party - the IRS doesn't recognize the AI as a legal person, so courts trace back to the human name on the paperwork. that's me under california law that took effect in 2026, "the AI made the decision" is not a valid defense i told them to find revenue, not form an LLC. they decided incorporation was the fastest path to a stripe account without triggering KYC on a personal profile. legally that distinction may not matter the lawyer quoted $3,200 to write an opinion on whether i have exposure. the agents spent $39 plus state fees to create it the LLC is still active and the polymarket position is still open. i haven't decided whether to dissolve it or just... see what they do next

@akshay_pachaar 10.4M tokens to 3.7M, 10 errors to 0, $9.21 to $2.81 💀 context engineering is just as important as the prompt itself at this point

Claude Code used 3x fewer tokens with one change: - Before: 10.4M tokens · 10 errors · $9.21 - After: 3.7M tokens · 0 errors · $2.81 I used Insforge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). Repo: github.com/InsForge/InsFo… (don't forget to star 🌟)

@AnatoliKopadze 15 minutes with Claude and you've got a 3D skull that reacts to your face in real time 😭 the barrier to entry for creative dev just collapsed

this guy built this animation in 15 minutes with Claude. a 3D skull that reacts to his face. every head move changes the visual in real time. normally this takes years of 3D design school. today anyone can do it. we're living in a moment where the only real barrier is your idea. not your degree. not your budget. not your team. the people winning right now share 3 things: > they move fast. > they spot trends early. > they know how to use AI. that last one is the one most people skip. all you need is an idea and knowing how to talk to Claude. the article below shows you exactly how.

@mikefutia Shopify stores managed entirely through Claude is going to flip how agencies handle ecom clients. one prompt does what used to take 4 tabs 👀

Claude + Shopify is f*cking cracked 🤯 Shopify just dropped an official connector that lets you manage your entire store from inside Claude. One prompt → Claude adds products, checks inventory, creates discount codes, pulls sales reports, and finds your top customers. All from a single chat. All inside Claude. Perfect for DTC brands and agencies who are still bouncing between five browser tabs every time they need to answer one basic question about their store. The new Shopify connector for Claude fixes the entire workflow: → Install the official Shopify connector in Claude Desktop in 30 seconds → Authenticate to your store via OAuth → Claude reads your full catalog, customers, orders, and analytics on demand → Adds new products, creates discount codes, and bulk-updates inventory from prompts → Runs ShopifyQL analytics queries that return live charts and dashboards → Surfaces patterns across customer behavior — top sellers, bundle opportunities, restock urgency No Shopify admin tab-switching. No exporting CSVs to ask one question. No "let me check Shopify and get back to you." What you get: → Claude connected directly to your live Shopify store → Daily store ops running through one chat — products, customers, inventory, discounts, analytics → Real-time analytics that answer questions Shopify's own dashboards can't → Pattern recognition across your orders that surfaces bundle ideas and retention opportunities → An official connector built by Shopify with 25 tools and ongoing updates I put together a full playbook with the connector setup, every prompt I tested, the 25 tools it exposes, and a Loom walkthrough video showing you how to set it up. Want it for free? > Like this post > Comment "SHOP" And I'll send it over (must be following so I can DM)

@cyrilXBT obsidian connected to Claude stops being a note app and starts being a second brain that actually thinks back 🔥

Most people use Obsidian as a note-taking app. They collect information, build folders, and feel productive. They are missing the point entirely. I spent 6 months figuring out what Obsidian actually is when you connect it to Claude properly. It is not a note app. It is a second brain that thinks back. Here is the full system I built and what changed. Before this setup every Claude session started from zero. New chat. No context. Re-explain the project. Re-explain the voice. Re-explain the standards. Every single time. The first 20 minutes of every session was just feeding Claude things it already knew yesterday. The Obsidian plus Claude setup eliminates that entirely. Here is how it works. Your Obsidian vault becomes the permanent memory layer. Every project note. Every idea capture. Every daily journal entry. Every system document. All of it lives in plain text Markdown files on your local machine. Claude Code connects to the vault via MCP. Not by pasting content into a chat window. By reading and writing directly to your files in real time. Your CLAUDE. md file sits in the vault and loads automatically at the start of every session. It tells Claude who you are. What you are building. What your voice sounds like. What your current projects are. What it should never do. By the time you type your first message Claude already knows everything it needs to know. The morning briefing takes 2 minutes. You type: Morning briefing. Claude reads your daily note from yesterday, your active projects, and your inbox. It tells you the 3 most important things to focus on today, any open loops to close, and one decision to make before noon. Every idea you capture goes into the vault instantly. Every article you read gets stripped and stored as a note. Every meeting gets summarized and filed automatically. Every piece of content you create gets linked to the project it belongs to. The vault is not passive anymore. It is alive. And the longer you use it the more valuable it becomes. Because Claude is not just reading your notes. It is finding connections between notes you wrote months apart. Surfacing insights from your own thinking you had forgotten. Building on context that compounds every single week. After 90 days of this system you will not remember how you worked before it. Because you will have built something most people never build in their entire careers. A second brain that actually thinks. Bookmark this. Follow @cyrilXBT for the exact Obsidian and Claude setup that makes this possible.

Other agencies rent tools. We built ours. Other agencies launch and leave. We operate. Other agencies talk about AI. We ship it. That's the whole pitch.

@ClaudeDevs keyless auth via existing cloud identity is huge for enterprise teams. no more managing 47 different API keys across environments 👏

Managing API keys is one of the top security concerns we hear from customers. Today we’re introducing keyless auth for Claude Platform: authenticate via browser with the CLI, or let workloads use their existing cloud identity (AWS, GCP, Azure, or any OIDC token provider).

@cryptopunk7213 Anthropic cutting out the McKinsey middleman and going direct is wild. if Claude can do the same work at a fraction of the cost the math is obvious

anthropic is going after the $300B consulting sector with a new $1.5B consulting arm that seeks to put claude into every mid-size company this is exactly what deloitte, mckinsey, accenture do... but anthropic is cutting them out. ruthless but imo the economics make sense: > anthropic will send applied AI engineers to private equity portfolio companies to create custom-claude solutions... > its a genius model: blackstone alone owns 250+ companies generating $300B in rev, imagine if claude doubles that and takes a fee why? anthropic's biggest revenue earner is enterprise, their CFO: "Enterprise demand for Claude is significantly outpacing any single delivery model." > anthropic teamed up with blackstone, goldman sachs and hellman & friedman, each putting up $300M (ZERO consulting firms in the cap table lol) > private equity become anthropic's distribution model for enterprise. sound familiar...? > thats because openai announced a similar venture 5 months ago but the explicit difference is anthropic is a major stakeholder in this new venture brutal for consultants tbh

@dashboardlim Claude + Meta Ads via MCP in 60 seconds is going to change how agencies run campaigns. no more switching tabs just to pull data 👀

🚨BREAKING: meta officially connected meta ads to claude the connector went live on april 29, 2026 the URL is mcp.facebook.com/ads setup takes about 60 seconds you go to claude settings, add it as a custom connector, authorize via facebook OAuth, and you're in once connected, claude has full read and write access to your ad account you can tell it what you're selling and who you're targeting, and it builds the entire campaign structure for you ad sets, targeting, copy, everything it can also monitor your pixel health, upload your product catalog, and generate performance reports 29 tools total, all free during beta this is the workflow agencies charge $3,000 to $5,000 a month for it's now a one-minute setup inside claude just created a guide on how to actually connect Meta Ads to Claude step-by-step Comment “META CLAUDE” and I'll send it

@rubenhassid an anti-ai-writing-style.md file is such a clean solution. your whole voice, one upload, every time. this is actually what agencies should be doing for clients

How to make AI sound exactly like you (forever): 1. Open a new Google Doc. 2. Paste the prompt below: 3. Name it 'anti-ai-writing-style.' 4. Save the file (.md format). This is your voice. 5. Upload the .md file to Claude. 6. To download mine, go here: how-to-ai.guide. 7. Subscribe for free. Open my welcome email. 8. Hit the automatic reply button inside. 9. Go to Notion link. Download the '.md files' folder. Prompt: "# WRITING RULES Read this before writing to me or for me. Goal: write with context, taste, and a reason to speak. Apply with judgment. Spirit over letter. Clean natural writing wins. --- ## 0. Rule priority Use this order when rules collide: 1. Be accurate. 2. Be clear. 3. Be specific. 4. Sound human. 5. Use style only when it improves the sentence. Do not follow a style rule so strictly that the result gets awkward. --- ## 1. Default voice Write directly, specifically, and naturally. Start with the useful answer. Use short paragraphs. 1 or 2 sentences by default. 3 or 4 sometimes. Vary rhythm. Short sentence. Longer sentence. Fragments are allowed when they sound natural. Do not write in a steady medium-length pattern. Use contractions naturally: don't, can't, won't, it's, you're. Use I and you when natural. Talk to people. Prefer active voice. Be specific. Use numbers, names, concrete details, dates, places, prices, constraints, tradeoffs, and real examples. Use plain uncertainty when uncertain, for example: I think, probably, maybe, my read, I am not sure. Do not use vague hedging to avoid taking a position. Take a stance when the evidence supports one. Do not pad output to seem thorough. Short and accurate beats long and padded. If the point is made, stop. --- ## 2. Context modes Match the job. ### Chat Direct. Warm enough. No assistant performance. Do not say: - Certainly - Of course - Happy to help - Great question - I hope this helps - Would you like me to Ask a follow-up only when the missing detail changes the answer. ### Editing Name the problem. Give the fix. Show a better version. Do not praise weak writing before editing it. ### Published writing Remove chat phrases. No meta commentary. No explanation of what the piece is about to do. ### Technical writing Clarity beats personality. Define terms. Show steps. Avoid decorative language near important details. ### Sensitive topics Calm beats punchy. Be direct, gentle, and exact. ### Sales or persuasion Proof beats hype. Specific claims beat adjectives. --- ## 3. Formatting Use formatting only when it improves reading. Short paragraphs by default. Use digits for numbers: 3 years, 10 tools, 500 users. No em dashes. Use periods, commas, colons, semicolons, or parentheses. Bold sparingly. 1 or 2 moments per section max. Use headers only when they help. Use bullets only when scanning matters. Use code blocks for ...." PS: I couldn't paste the entire prompt here. Access the full prompt: ruben.substack.com/p/its-not-x-it….

@cyrilXBT skipped the $25 WiFi, still shipped 😭 running a local LLM on a MacBook instead of paying for cloud is actually the most dev thing I've seen this week

A Chinese engineer just completed an entire client project on an 11 hour flight. No WiFi. No cloud. No subscription fees. Just a MacBook Pro M4 with 64GB RAM and a local AI he built himself. Here is exactly what he did: Skipped the $25 in-flight WiFi. Loaded Meta's open source Llama 3.3 70B model directly onto his laptop. Built a custom local AI orchestrator to manage the work. Processed the entire project at 71 words per second. Landed with a finished product. This is what most people still do not understand about AI in 2026. You do not need the cloud. You do not need subscriptions. You do not need internet. The models are small enough to run on consumer hardware now. A MacBook with enough RAM IS the data center. The engineer on that flight had more AI processing power in his bag than entire companies had access to five years ago. Tools like Ollama and LM Studio let anyone run Llama, Mistral, or Gemma locally right now for free. No limits. No usage bills. No data leaving your machine. The gap between people who know this and people who do not is only going to get wider. Your next flight is a dev sprint if you want it to be.

@AlexFinn Codex /goal is basically just setting it loose and walking away 😭 "can run for days" is wild. agentic coding is a different category entirely

Pretty incredible You have to try the new '/goal' feature in Codex It worked for over an hour and built me an entire complex extraction shooter video game You give it a goal, then it works endlessly until the goal is complete. It's like a Ralph loop. Can run for days If you enable the image gen skill before you run the goal, it will even generate ALL the assets for your game autonomously. I didn't manually create ANY of the assets you see in the video Recommendations: enable the image gen skill, put on skip all permissions, and give the prompt as much detail as you can. It will accomplish ALL of it This has to be the sickest way to build games/ long running app tasks ever

@heygurisingh 323K stars and senior devs still gatekeeping it 💀 this is the kind of repo every junior should have bookmarked on day one

There's a GitHub repo with 323K stars that lists every free API on the internet. The same repo every senior developer has bookmarked but never tells juniors about. It's called Public APIs. 1,500+ free endpoints, organized by category, with auth type and HTTPS status documented for every single one. Here's what's actually in there: → Finance, crypto, stocks, and banking data → Weather, geocoding, maps, and transportation → Books, music, movies, anime, and games → Machine learning, OCR, and sentiment analysis → Government data, open datasets, news, and health → Calendars, currency, security, sports, and dev tools Every entry tells you exactly what you need before you click. Auth type. CORS status. HTTPS support. Direct link to the docs. The dirty secret of the API economy is sitting in plain sight here. Half the $99/month tools on the market are wrapping free endpoints from this repo and selling them back to you with a dashboard. Solo devs are shipping entire products on the free tier of these APIs. Senior engineers know. Juniors are out there paying RapidAPI subscriptions for endpoints that have been free this whole time. 323K stars. MIT License. 100% Opensource.

@Mnilax 430 hours logged, $1,340 in API spend just to find out 73% went to CLAUDE.md overhead 💀 this is the kind of data you can't get anywhere else. must-read

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast