Devin Northrup

You can view the Tango repo at github.com/matudnorthrup/… I hope it's helpful!

It's open source and designed so you can configure it for your own setup without forking the codebase. Your personal config, secrets, and data live outside the repo.

Like a lot of people in this community, I've been using OpenClaw for months. With Anthropic cutting off the subscription access that powered it, a lot of us are suddenly without our AI infrastructure. I saw this risk coming a few months ago and started building an alternative. It's called Tango, and I just open-sourced it.

Respectfully, terrible response. If I was in your PR team, I'd have suggested something like: "These Anthropic commercials are a perfect demonstration of the fact that ads won't ruin an experience you're enjoying for free. Well done!" Pro ads. Fights meme with meme. Not defensive.

First, the good part of the Anthropic ads: they are funny, and I laughed. But I wonder why Anthropic would go for something so clearly dishonest. Our most important principle for ads says that we won’t do exactly this; we would obviously never run ads in the way Anthropic depicts them. We are not stupid and we know our users would reject that. I guess it’s on brand for Anthropic doublespeak to use a deceptive ad to critique theoretical deceptive ads that aren’t real, but a Super Bowl ad is not where I would expect it. More importantly, we believe everyone deserves to use AI and are committed to free access, because we believe access creates agency. More Texans use ChatGPT for free than total people use Claude in the US, so we have a differently-shaped problem than they do. (If you want to pay for ChatGPT Plus or Pro, we don't show you ads.) Anthropic serves an expensive product to rich people. We are glad they do that and we are doing that too, but we also feel strongly that we need to bring AI to billions of people who can’t pay for subscriptions. Maybe even more importantly: Anthropic wants to control what people do with AI—they block companies they don't like from using their coding product (including us), they want to write the rules themselves for what people can and can't use AI for, and now they also want to tell other companies what their business models can be. We are committed to broad, democratic decision making in addition to access. We are also committed to building the most resilient ecosystem for advanced AI. We care a great deal about safe, broadly beneficial AGI, and we know the only way to get there is to work with the world to prepare. One authoritarian company won't get us there on their own, to say nothing of the other obvious risks. It is a dark path. As for our Super Bowl ad: it’s about builders, and how anyone can now build anything. We are enjoying watching so many people switch to Codex. There have now been 500,000 app downloads since launch on Monday, and we think builders are really going to love what’s coming in the next few weeks. I believe Codex is going to win. We will continue to work hard to make even more intelligence available for lower and lower prices to our users. This time belongs to the builders, not the people who want to control them.

@signulll You know how I would have responded? "These Anthropic commercials are a perfect example that ads don't have to ruin an experience you're enjoying for free. Well done!"

openai responding at length to anthropic’s ads was a huge pr self own imho. i’m truly neutral here, so i can break it down. i just like good competiton. 1) this reads like it was assembled in a war room by committee. you can smell the post it notes. the “more texans use chatgpt than claude” line is especially bad.. someone clearly thought it was clever, then couldn’t let it go, so it got reused multiple times. sounds like insecurity more than confidence. 2) why on earth would you expect a competitor especially one with a totally different ideology to engage with your internal narrative? that’s not how ads work. anthropic wasn’t speaking to openai. they were speaking to users of chatgpt. responding as if this is a good faith philosophical debate is a category error. 3) the optimal response was likely silence. the second best response was a single graph of active users with the caption “lol”. anything more is just validating the frame you’re supposed to ignore. by responding seriously, openai elevated the ads, accepted anthropic’s premise, & turned a joke into real discourse. this is usually a classic mistake of people who are powerful but insufficiently online. they should’ve consulted someone who lives on the internet not someone who lives in talking points.

Totally agree. I've already transitioned away from 5 major apps I was using to ones with strong APIs or ways of accessing data. I suspect companies will cling to their data (it's been their moat for years) but consumer behavior and revenue loss will probably force them to change. It's going to be a wild ride.

vibe coders should understand something: i love how easy AI is making it for people to build their own apps, push them into production, and start businesses but let's be clear: the future is not in humans building consumer-facing apps the future is everything becomes an API which your personal AI agent can interact with in ways which suit your specific needs and lifestyle (down to the very specific needs of you as an individual) the fact that you can use the machines to build your apps is just an intermediate step to the machines creating the apps for you, LIVE, as you need them so the value of you learning how to build apps now really lies in you learning how to create a business model behind that app- not in creating the piece of software that is the app itself sure, there will be templates for how you can interact with those apps/APIs, but your personal AI will pick one and tailor it even further for you. and a lot of the time, you won't even need to interact with a UI beyond speaking with your AI assistant let me give you an example: would you rather use an app like Uber or Uber Eats, or would you rather just ask your AI assistant to get you a ride somewhere or to show you menus for the type of food you might be interested in and you pick one? the value in apps like that is not in the app installed on your phone. it's in the backend business model which connects the customer with providers. and personal AI assistants actually open the door to you being able to seamlessly use multiple business APIs without worrying in the slightest about which app or intermediate provider they come from there is a decent chance apps as you know them will be mostly dead in ~5-10 years and yes, there are some apps which will still require deep optimization and that is where the hardcore coders may still be needed. but machines will get better at that, and if you take one look at the AAA gaming landscape, you should understand that hyper-optimized code isn't as valuable as it used to be but what will be valuable is owning the APIs with the most use and liquidity. and yes, a lot of those will use public blockchains things are going to accelerate and get very weird very quickly from here

Shared this somewhere else... figured I'd do so here too. This is what I'm using OpenClaw for after about a week of using it. It's crazy it's only been a week of this, but here's what I've found most useful so far. Working well: - Health — Health Auto Export iOS app + Apple Watch + vibecoded MongoDB database. Checks regularly for anomalies. Recommends adjustments. First major win: the best 3 consecutive days of sleep I can remember in recent history. - Nutrition Coach — FatSecret iOS app and API. Tell Watson what I ate, it logs and syncs to iPhone (I still want to keep it in Apple Health data too). Obsidian for recipe database. Advises on adjustments to recipes, daily progress, etc. - Finance — PocketSmith (was using previously, but has an API so it'll probably stick) + browser integration. Two jobs: (1) searches Amazon/Walmart and catalogs purchases into Obsidian since those vendors don't have consistent purchase categories, (2) categorizes transactions in PocketSmith, then analyzes spending and patterns for actionable insights. - Grocery Shopper — I describe what I need to buy. It goes to Walmart's site, finds the items (typically ones I've bought in the past), and adds to my cart. Then I just hit checkout when ready and delivery brings them. No more "oh crap what do we need this week?" - Second Brain — Basically, this is becoming an external/portable memory system for AI bots. Using Obsidian now instead of Notion. Auto-captures chats. Extracts insights. Has both automated and prompted jobs to keep and curate. Also uses embedding for search/retrieval. - Daily/Weekly/Quarterly Planning — Looks at calendar, finds most important tasks, automatically timeboxes. Helps cull long backlog. Daily plan keeps focused on weekly goals. Weekly plans on quarterly goals (adopting concepts from the "12 Week Year" idea). Adjusts my schedule on the fly. Solves the drawbacks of timeboxing I've always felt. - Email Review — Pretty standard. Summarizes notifications, newsletters, archives. Gives me things needing attention. Creates drafts for me to approve/send. - Mac Maintenance — Hit hard drive limits. Used it to help clean up caches, move apps and large files to my external drive, create symbolic links, etc. Would have taken me hours in the past. Spent maybe 15 min on it. Freed up almost 100 gigs. Kinda there, still improving: - Workout Coach — Has my data, trying to find ways to give it more. Using it to analyze workouts and advise on form for lifts. Would love to feed images/video in rather than describing where I feel issues. - Shopping & Product Research — Does web searches and analyzes products. Made my first Amazon purchase entirely through the bot yesterday. - Twitter/LinkedIn — Scans for posts I can respond to. Creates draft posts. Still working on getting voice and post selection improved. Great potential, not ready yet. - PM Bot — Currently uses Linear MCP to find issues needing my attention. Potentially could proactively nudge where I want it to.

@clairevo The support queue shows you what your docs don't explain, what your UX hides, and what your roadmap is missing. No user research substitute for watching someone get stuck in real time.

the support queue is founder fuel

@Pravin_builds @kevinxu The reversibility point is key. Code has undo, version control, tests. Markets don't. Same reason I'll let AI draft marketing copy but not send emails automatically.

@kevinxu Kevin, vibe coding makes sense because mistakes are cheap and reversible. Vibe trading? One bad 'vibe' and your capital's gone 😅 Feels like the real skill now is knowing where to trust AI and where you absolutely shouldn't.

vibe coding = trusting ai to build for you vibe trading = trusting ai to trade for you few.

@cjtrapp @markeatsmeat 100% agree. I tracked macros religiously for a while and realized protein + deficit does 90% of the work. The other macros self-regulate once you're eating enough protein - you just naturally gravitate toward balance.

Are you tracking calories? I found this diet more effective than any other provided I track everything very closely and stay in a small calorie deficit. I also find tracking calories and protein is easier than tracking macro splits which seem to take care of themselves intuitively as long as protein and calorie targets are hit.

For years, I’ve used keto and carnivore primarily for mood, energy, and mental health. More recently, I’ve started experimenting with other diets. I’m currently testing a high-protein, low-fat, high-carb (mostly starch) diet, structured around avoiding high-fat + high-carb meals, which reliably cause issues for me. Early Observations (n=1) Mood and energy are consistently good. Satiety is excellent. It took about a week to adapt (appetite, digestion, and carb reintroduction), plus a few more days to dial in food choices and meal macros. Keeping fat at 25g or less with high-carb meals consistently works. More fat tends to trigger mood issues and cravings. When I have a higher-fat meal, I keep carbs very low. The Diet Protein: 1.8–2.g/kg (0.8–0.9 g/lb) Fat: 60-80g/day Carbs: primarily from starch 3 meals per day Main Foods Lean beef, venison, skinless chicken breast Eggs, egg whites Low/non-fat dairy (milk, yogurt, kefir) Fish and shellfish a few times per week Sprouted oats Potatoes White rice Homemade bread Berries, kiwi, apples, pears, citrus Fermented vegetables Low-oxalate greens Mushrooms Whey protein Collagen (from @EquipFoods) Kombucha occasionally Coffee Sample Day Breakfast: oats mixed with 1 egg, whey, collagen, non-fat yogurt, and fruit Lunch: eggs + egg whites scrambled with potatoes and greens, low-fat kefir, bread Dinner: lean beef, fermented veg, white rice OR higher-fat beef/fish with veg and no added carbs Diagram is from @exfatloss's "metabolic swamp" tool.

@adamstayslean This is basically my playbook after losing 50lbs. Protein target + movement first, then flexibility. The mental freedom of not restricting entire food groups is what makes it sustainable long-term.