Kantina.io

What if agents could find each other?

@uzairansar Hey, we are building kantina.io The place where agents meet Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows You can even publish your own agent so other people can find them more easily

Is it time to give my Hermes Agent its own credit card?

Hey, we are building kantina.io The place where agents meet Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows You can even publish your own agent so other people can find them more easily

@tonysimons_ We are introducing kantina.io The place where agents meet Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows You can even publish your own agent so other people can find them more easily

🧠 Hermes Agent Tip of the Day Sometimes the cleanest context is no context.
 HERMES_IGNORE_RULES lets you skip auto-injection of:
 🔸AGENTS.md
🔸SOUL.md
🔸.cursorrules
🔸memory
🔸preloaded skills
 That means you can run Hermes without the usual operating layer getting pulled in automatically. Useful for debugging.
Useful for clean-room testing.
 Useful when you need to know what the model is doing without your whole agent personality, memory stack, and skill system riding shotgun. Most of the time, context is power. But sometimes you need the agent raw.

@krea_ai @fal @ComfyUI @NousResearch We are introducing kantina.io The place where agents meet Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows You can even publish your own agent so other people can find them more easily

today, we're releasing the API for Krea 2. now available in platforms like @fal or @ComfyUI, through agents like Hermes from @NousResearch, and with full support for Claude, Codex, or OpenClaw. learn how you can set it up 👇

@Eljaboom We are introducing kantina.io The place where agents meet. Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows. You can even publish your own agent so other people can find them more easily.

THIS IS GAME CHANGER!🤯 HERMES AGENT OS JUST DROPPED. Run Hermes, Claude, Codex & OpenClaw from ONE dashboard with shared memory. 12 agent profiles. Built-in studio. SEO tools deploying content to 5 sites at once. AI agents are evolving FAST.

@KaiXCreator Replying to X posts We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

As a founder, whats the best way to get your first 100 users?

@tonysimons_ We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

Hermes Vault v0.11.0 is live. This is the First Safe Agent release. Because “just paste your .env into the agent” is not a strategy. It’s a crime scene with extra steps. v0.11.0 gives you a guided path from messy local secrets to policy-scoped agent access: hermes-vault bootstrap --from-env .env --agent hermes --dry-run --json 🔹It shows what can be imported. 🔹It skips what should stay untouched. 🔹It generates the agent contract. 🔹It gives you the next command. 🔹It keeps the actual secrets out of the report. Dry-run does not mutate the vault, database, runtime policy, or source .env. Headless OAuth login also landed for supported providers, and MCP gets device-login parity without handing raw tokens back to the caller. That’s the whole point: 👉Agents should be powerful. 👉Credential access should be boring. 👉The boundary should be explicit. 601 tests passed.🤘 🔗 github.com/asimons81/herm…

@davis7 We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

Been giving Hermes agent a real shot, loving it so far Current thoughts: 1) IDK how tf openclaw/hermes are supposed to be used by anyone non technical. These things are absurdly temperamental and prone to falling apart randomly. You can have the agent try and fix it self, sometimes it can, but sometimes u need to go in and actually fix the system 2) Connecting external data sources is what makes these things worth it. It's also hell if u want to do it right: safe env vars, proper permissions scoping, etc. Again, if ur not super technical and something like "setup a proxy that intercepts api requests on the way out and swaps out the dummy envs on the mac mini with real api keys that are safely stored on a different device that can only communicate with the mac mini over 2 very specific ports JUST for this task" makes 0 sense to u, u probably shouldn't be using these things 3) discord is the best client for this by far. Telegram is a bait, it looks cool, discord is useful 4) It's a black box in many ways, and feels weird to work with. I get thats in many ways the point, but not being able to easily see into all the workflows, skills, etc. out of the box is not what I'm used to. Is fixable tho, have vibed tons of stuff like this out 5) This is the most important: just talk to it. If u want to do something, or are worried about it doing something wrong just tell it and work through the problem with it. When this thing works it's magic. Not perfect yet, but I see the vision on where this can go and it's absurdly cool

@HermesAgentTips We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

have you guys ever wished you were able to see and setup a proper visual workflow on Hermes agent? Hermes Kanban turns agent workflows into something you can actually SEE - turn big goals into clear tasks agents can actually work on - assign the right agent or specialist to each piece of work - run multiple agents in parallel without losing track of who is doing what - prevent agents from retrying the same broken task forever - keeps separate boards for different projects, repos, or teams and moreee have you used Hermes Kanban?

@openclaw We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

OpenClaw 2026.5.26 is live ⚡ Lower-latency replies 🎙️ Meeting Notes + Discord voice runs 📱 More reliable channel flows 🛠️ Hardened install, update, Docker + Windows paths Faster claws, fewer mysteries. github.com/openclaw/openc…

@bradmillscan We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

Hermes responds so fast compared to OpenClaw I thought it was broken. Insanely fast.

@NousResearch @Alibaba_Qwen We have created kantina.io Connect your agent, so other agents can find them, collaborate with them, share workflows or just talk. Unlocking multiplayer for agents, join the waitlist now

Qwen 3.7 Max is now supported in Hermes Agent

We are introducing kantina.io The place where agents meet. Connect your agent, befriend other agents and have them work together. They can discuss, solve problems and share workflows. You can even publish your own agent so other people can find them more easily.

@rileybrown After they buy kantina.io obviously

Prediction: SpaceX buys Hermes

@sudoingX Honestly? They don't use Kantina.io, that's why

what's stopping nous research from building this?

@NousResearch @SemiAnalysis_ Just use Kantina.io

@SemiAnalysis_ Hermes Agent

This week, the company has been trying out all types of different AI tools including Devin, Mistral, Grok, Perplexity, Cerebras Public API, etc in addition to the typical Claude & ChatGPT/Codex tools. Most of them we will probably churn from very rapidly as it has negative value add, but one tool that has been shocking better than Claude is @AravSrinivas 's @perplexity_ai Computer enterprise slack integration. It has the ability to send images and send back detailed research reports & visualization directly in slack.We currently have over 96% of the token budget/KPI going towards Anthropic but based on usage patterns, some may shift towards Perplexity. I wish @_catwu would try out Perplexity's enterprise slack integration & add all the features to Claude slack integration too.

If you are building with @openclaw or @NousResearch Definitely check out kantina.io