Ripquid

@aridutilh we’re building automated improving intelligence layers aideapp.dev

we're investing $100,000 in solo founders building something that feels like their calling. paying customers are great but not required if moonshot. dm me if this is you – let's work together.

@RaphaelDabadie applied! aideapp.dev

Who’s applying to YC S26 ? 👀

@S_N_SH_E_ No, if there’s no money, there’s no value to what you’re building. Money is a measurable way to say yes people want this, and it solves some sort of problem.

Be honest: If you removed money from the equation, would you still choose this path?

@S_N_SH_E_ Mix of both, this assumes they are mutually exclusive.

genuine question self-taught devs using Claude + Codex vs CS grads who understand fundamentals who actually wins in the next 3 years ?

@zachtratar @zachtratar we augment notion and obsidian by making them automatically queryable using relational,graph, and vector embeddings. Allowing users to spawn fleets of smart agents. Become the 100x developer aideapp.dev

Have you tried Notion?

@shawmakesmagic @shawmakesmagic That’s why we made a shared brain for AI. Agents are dusconnected, they work better when sharing skills, memories, and tools. We made it so agents use the brain automatically and it evolves without user action. Become the 100x dev aideapp.dev

Once you have an agent, the next social network is emergent

@rxhit05 @rxhit05 AI brain that can make everyone a 100x dev. Manage skills and memories to orchestrate fleets of agents that ship faster and better code the more you use it. Already talked to engineers from Google, Amazon…We have a pilot with Arena ai. aideapp.dev

Hey founders 🚀 🚀 🚀 Looking to connect with people building in: 💻 SaaS ⚙️ Tech 🤖 Automation 🧠 AI tools 📦 Product Development 🌐 Web apps Drop what you're working on 👇🏼

@Teknium @Teknium This is smart! My app should be able to do the autonomous avalanche in one go. My app spawns Hermes agents with gstack design docs to ship at 100x speed. Gunning for autonomous avalanche? Orchestrate and ship your fleet in under a minute here: aideapp.dev

Testing out some of the dashboard plugins for the contest we ended yesterday, this one's pretty great

@Luiz__Matthias @ZabihullahAtal One command! npx @agenticide/install Install, create an account, go!

@ripquid @ZabihullahAtal I'm interested. How to see your work?

🚨 BREAKING: A new role is quietly emerging and it’s about to dominate the next 5 years. It’s not “AI engineer.” It’s not “prompt engineer.” It’s the Agent Operator. And it will sit inside almost every organization. Most people are still thinking about AI as a tool. That framing is already outdated. What’s actually happening is a shift from: humans using software to humans managing autonomous agents that execute work This is a fundamental redesign of how work gets done. So what is an Agent Operator? An Agent Operator is the person who: • Designs how agents interact with real workflows • Connects tools, data, and systems into agent pipelines • Translates business problems into executable agent behavior • Monitors, corrects, and improves agent performance over time They don’t just “use AI.” They orchestrate outcomes. and this matter because Every function marketing, legal, finance, biotech is becoming “agent-compatible.” Not because companies want it. Because they won’t have a choice. Agents can: • Run research loops • Execute multi-step workflows • Integrate across tools without APIs breaking the flow • Operate 24/7 at near-zero marginal cost The bottleneck is no longer capability. It’s implementation inside real-world systems. Required skills for AI Agent Operator role: → MCPs (Model Context Protocols) Understanding how agents access tools, memory, and structured context. → CLIs (Command Line Interfaces) Because serious agent workflows won’t live in GUIs—they’ll run in programmable environments. → Writing skills (the file kind) Clear specs, instructions, and structured documents. Agents run on precision, not vibes. → agents dot md fluency The ability to define agent roles, constraints, memory, and tool usage in persistent formats. → Business acumen Knowing what actually matters: Where automation creates leverage, not noise. What happens next Enterprises will begin to redesign workflows: Not around employees using dashboards… But around agents executing tasks. That means: • SOPs → Agent playbooks • Teams → Human + agent hybrids • Tools → Composable agent systems When that shift happens, companies won’t just need engineers. They’ll need operators who understand both the system and the business. The leverage is asymmetric One strong Agent Operator can: • Replace fragmented SaaS workflows • Multiply team output without adding headcount • Turn ideas into execution systems in days This is not incremental productivity. It’s operational transformation.

@kevinwtung @kevinwtung We’re building the self evolving brain that connects the all the agents. Orchestrate and deploy fleets of agents that automatically use skills and memories! Become the 100x developer aideapp.dev

We’re using gstack for our autonomous agents as well! Ship a design doc with office hours or auto plan , orchestrator agent reads, deploys parallel Hermes agents, review and improve on the plan, repeat. It destroys time estimates, 27 commits and 4k lines of code shipped in 1hr

@ycombinator @garrytan Hey we saw the call for the AI brain that can power companies agents. We’re building a the evolving knowledge to store memories, skills, and documents agents use automatically. More info on our website: aideapp.dev

@ycombinator Now everyone can be as productive as the best AI engineer and can automatically share knowledge between agents. Users just boot up the app and they’re connected. We’ve talked with engineers from Google, Lockheed, and Amazon. We have a pilot with Arena.ai

@ycombinator We then extended this idea to make a fully autonomous brain. An app that can learn, evolve, and improve itself. Quality control is easily manageable through skills. We’re able to ship code at 100x speed now, orchestrating fleets of agents

AI has stopped being a feature and started being the foundation. We're excited about a new wave of startups rebuilding software, services, and silicon— and pushing AI into the physical world. ycombinator.com/rfs

@hthieblot A shared evolving brain agents can access and contribute to. Currently using it to write code autonomously while using the brain to manage technical debt. It’s shipped 57 new features, 70 skills, 40 memories over an 8hrs using gstack, auto research, and Hermes. Old prototype ^

The longer I'm on X, the more I realize: Founders with small accounts are the most interesting ones. - too busy building to posture - 0 Ego, they just wanna win - keep posting with 0 likes - the world isn’t rooting for them yet but I will Tell me what you are building

@rezoundous Hold my beer

Does anyone actually run 20 agents in parallel?

@shannholmberg 20 minutes is too long, I’m making an app that does it better in 30 seconds aideapp.dev

you lose 2 hours a week re-explaining yourself to AI. your voice, your audience, what you're working on, what worked last time. context that should already be there. and you know what fixes it. you've seen the posts, karpathy's knowledge base, the obsidian setups, the second brain threads. you bookmarked them. but you haven't set it up yet. not because it's hard, it takes 20 minutes, not because you don't have the tools, you have a claude subscription, obsidian is free, the framework is open source. you haven't done it because prompting from scratch still feels like progress. you're moving, typing, getting output, but you're burning tokens reprompting and adding context just to get anything near a good output. that's a trap, 20 minutes of setup saves you at least 2 hours a week, every week, compounding. but the reprompting feels normal because you've always done it. I wrote a full breakdown of how the knowledge layer works, how to build one for content, for a company, and for your personal life. the system takes 20 minutes to set up, procrastination can cost you 100+ hours a year.