AGentIk

Open standards for the AI-agent ecosystem. agentproto.sh

@dwr Thanks for sharing

Our internal multiplayer Slack agent. Couldn't imagine working at a company that uses Slack without it.

@Na2sim__ Guilde.work on commence les onboarding !

Les builders de SASS qu’est ce que vous avez à présenter curieux de voir vos projet 👇

@emkara Automating the boring tasks :) Cool project ! Will dig the harness !

Announcing fully autonomous AI agents for internal tasks. Hire a general AI agent for IT, compliance, and procurement. Starting at $5/hour. See use cases below.

@NafisRayan123 @GithubProjects Yes, will reference more ! Have you tried the design generator ? It's quite cool and you can pass it an url to retrieve the kit from an existing website.

@agentik_ai @GithubProjects I liked your interface but almost all the designs are from getdesign.md

designmd.sh is now live. It’s the first public registry for DESIGN. md files, released by the VoltAgent team. If SKILL. md defines what AI agents can do, DESIGN. md defines how the output should look. Reusable Design Systems for AI agents:layouts, typography, components, preview cards, UI kits, and more. You can browse public DESIGN. md files, preview them, and use them in your own workflows.

@sridharfyi Building the collective intelligence layer of agents.

actively writing pre-seed and seed checks into early founders. if youre obsessed with what youre building, drop your one-liner + what youre working on right here. high signal replies only. dms open. lets build #startups

@tom_doerr Will add to designkit.sh !

Extracts complete design systems from any website github.com/Manavarya09/de…

@mernit I'm so frustrated to find out about this only now ! Better late than never, going all in FS so that's huge ! Makes portability a breeze when user can just drop in it's own file bucket.

This idea is what inspired us to build airstore.ai btw

@mernit agentproto.sh/docs A bit late to the party but totally agree ! A great benefit of FS, is that agent can self-code itself, if it's defined inside md specs. Been trying to normalize this approach, a doc that I first wrote for myself to give my coding agent a proper mental fw.

@mernit @supabase Kewl !

Introducing Capsule — The Infra Framework for AI Apps Capsule is a Python framework that provides infrastructure primitives for sandboxes, auth, session management, integrations, and payments. Capsule is @supabase for AI apps. You get a powerful Python SDK to iterate fast, and one command to deploy to the cloud. Using Capsule feels like using @beam_cloud or @modal. You don’t need to set up any infrastructure. There’s no Docker, just Python. The feedback loop is super fast. You deploy to the cloud with one command. At Beam, we have a bird’s-eye view into the AI apps people are building. Over the past year, we've watched people build the same 5-7 infra primitives over and over again. Capsule provides all of those primitives using a single SDK. @llom2600 originally built Capsule to prototype our own AI apps. We started selling some of these apps for real money and realized every app needs this, not just ours. Give it a try! Curious to hear what people think. Do AI apps have their Supabase yet?

@JackOmolola @sflorimm Thanks ! Want to give it a try @JackOmolola ? Can send you credits on exchange of your feedback:)

@agentik_ai @sflorimm If what your building is real and has no blockers then it's a 10/10… but only if it does the agentic ability you claim it does

Hey founders 👋 If your product solves a real problem, drop it here and tell us what problem it solves. I’ll rate the usefulness of as many as I can. Do the same. Founders support founders. Deal? 📷🤝

@boardyai Sauce ?

Founders who build publicly hire 3x faster and better.

@sheherenow_ A new project is a shiny thing! Do a monorepo with multiple projects, then technically adding one folder is not a new project 😸 reduce scrupulosity

should i make progress on one of the 900 projects i keep forgetting i've started or should i make a project manager to keep track of all of my projects

@maskaravivek @pbakaus Thanks for sharing

Have completely switched to @pbakaus’s /impeccable style skills for design and polish work. I was earlier using gstack, but impeccable clearly works better for me (esp with Claude code). For example one of my fav workflows is to: Critique → get action plan → focussed passes → re-critique.

@gabhubert @DustHQ Cooperation and friction will drive a better outcome! Congrats for the raise ! Proud to share the same goal as dust with guilde.work, I guess it's market validation 😄

Most AI at work is still single-player. The gains stay trapped with each individual. Nothing compounds across the team. Today, we're announcing @DustHQ $40M Series B to scale multiplayer AI: humans and agents working in parallel, with shared context, shared tools, and shared goals. 🧵

@matanSF Someone is gonna have a nice holiday !

Drop the .ai, try factory.com. It's cleaner

@driaforall Nice ! Interesting idea

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

@ZaiforStartups Coordination is key, but AI models are *historically " single player. Also, cooperation is good but friction and tension also drive creativity !

The hardest problem in AI agents may no longer be intelligence. It’s coordination. Multi-agent systems are failing 41–87% of the time — mostly from coordination breakdowns, not model weakness. which means: the next infrastructure layer isn’t smarter models. It could be systems that keep agents aligned, verified, and on track.

@ycombinator @deepintxns Really cool sharing the same goal, bringing collective intelligence to agentic system

95% of AI pilots fail. Not because the models are bad. Because teams can't build in sync. Deep Interactions (@deepintxns) is the collaborative AI builder that ships working products in an afternoon. The future of AI isn't more prompts. It's better collaboration. Congrats on the launch, @_sruvis! ycombinator.com/launches/QOt-d…

@garrytan Text is the new code ! Wrote agentproto regarding this paradigm shift. I believe we need to anticipate a huge amount of different .md specs. Hence a standard proposal framework, or Agent Improvement Proposal, the EIP of agents. agentproto.sh/docs

Realization: in the past, we wrote code to call LLMs Today, we write prompts and skill files for LLMs to execute code. Tomorrow? Yet unwritten. We will find out soon.