Dale Thomas

@LoicBerthelot Hermes for the win hands down. With Kimi K2.6 its awesome. And I have it in @MulticaAI and it makes it even better.

My honest comparison of OpenClaw vs Hermes: LEARNING… > OpenClaw uses static, human authored skills. > Hermes refines skills with a self improvement loop. 👑 Hermes → (1-0) MEMORY… > OpenClaw has basic memory. > Hermes has multi-level memory and cross-session recall. 👑 Hermes → (2-0) SKILL ECOSYSTEM… > OpenClaw has 50+ built in skills and easy plugin. > Hermes has 40+ tools and autogenerates new skills. 👑 Tie → (3-1) CHANNELS… > OpenClaw supports everything. > Hermes has a much smaller integration base. 👑 OpenClaw → (3-2) MODELS… > OpenClaw supports Claude, GPT, Gemini, Grok, etc… > Hermes supports 200+ models with OpenRouter… 👑 Hermes → (4-2) DEPLOYMENT… > OpenClaw runs local, VPS, cloud w/ managed options. > Hermes runs local, VPS, Docker, SSH, and serverless. 👑 Hermes → (5-2) SECURITY… > OpenClaw has had multiple critical CVEs in 2026. > Hermes has zero agent CVEs so far. 👑 Hermes → (6-2) AUTOMATION… > OpenClaw has heartbeat scheduler, cron jobs w/ multi-channel workflows. > Hermes has natural language cron w/ parallel sub agents. 👑 Tie → (7-3) — Hermes wins. And that’s why I transitioned away from OpenClaw completely. Which one are you all using? Curious…

@jiayuan_jy @MulticaAI Actually, the issue that I was seeing had nothing to do with Multica. Was able to resolve that this morning.

@dalethomas50 @MulticaAI feel free to share any feedback

Started play with multica.ai today! This is the sweet spot in having agents in a project management tool. Running Claude Code and Hermes agent and can't want to use Multica more. @MulticaAI

@NousResearch I did sign up for the $10 plan just to play with it. But is there any advantage of going through you vs. OpenRouter?

New subscription tiers are live on Nous Portal → Plus ($20) → Super ($100) → Ultra ($200) Bonus credits on signups, upgrades, and renewals: +$2 on Plus / +$10 on Super / +$20 on Ultra All tiers include access to: → 300+ models → Bundled tool usage portal.nousresearch.com/manage-subscri…

@jiayuan_jy Do you all have a Discord channel or any type of place to ask questions? I am using this with Claude Code and Hermes.

We created the open source version of Claude Managed Agents. Introducing Multica github.com/multica-ai/mul…

@sorzy5 @jiayuan_jy @NousResearch I just started using it with Hermes to and it's pretty slick.

@jiayuan_jy @NousResearch Damn I want to see that ! Thanks for this 🙏

@jiayuan_jy @Mossiah Definitely NOT the same thing!

@Mossiah not the same thing

@JustinqReid Karen and I were having lunch at the club and watching you at the golf tournament!

The pick is in ⏰

@RoundtableSpace Hermes. It just gets shit done.

HERMES AGENT IS NOW GAINING MORE INTEREST THAN OPENCLAW > open source > self-improving > runs local > remembers everything Which one are you using?

@QualitativAi @Teknium Thats exactly what I was going to say and the first thing I checked when I saw this post.

@Teknium I found out Ollama Cloud has it!

Kimi 2.6 looks like it could be the new contender for best open agentic model for Hermes Agent, stacking up strongly against even opus 4.6 in these agentic benchmarks 😲

@oliverhenry Hermes, @NousResearch , for the win! FTW!

Hermes is a psyop, i have not seen a single account recommend it that doesn't look like a bot OpenClaw 4 lyf

@eliana_jordan Open what? What's that?

openclaw or hermes for marketing?

Using OpenClaw is basically is like driving your own Ferrari (that you have to be a mechanic for yourself) and it's broken down all the time, but gives you the time of your life vs driving a reliable Honda (Hermes Agent) vs riding the bus (Claude / ChatGPT)

@imranye Oh! That reminds me that I need to get that up and running on my Android phone.

mac minis are sold out everywhere, but android phones are a dime a dozen. i’m installing hermes agent on my solana seeker will update with how the experience is

@icanvardar That is still a thing? Isn't that the MySpace of 2025?

only 8 people were impacted in total

@nesquena @Teknium @NousResearch It is a Windows / MAC / Linux app? I would be happy but I am on Windows.

Was able to get a slick native swift desktop app v1.0 up and running for Hermes agent today (credit to redsparklabs) Can I get a few people to alpha test it with me? Works great for me so far! 🚀 DM me! @Teknium @NousResearch Check out this beauty!

I used to think Opus 4.6 and Claude Code was a beast and then I met Manus.ai. Now I have met Hermes Agent, @NousResearch , and holy shit! Hermes Agent is the GOAT! There I said it!

@nobitoshii @NousResearch @Zai_org I would agree with that assessment.

@nobitoshii @NousResearch @Zai_org I must have really bad tastes because while its useful and functional I personally don't find it appealing to the eyes.

@PaulGugAI I am using this with Hermes and agree my Hermes agent said it would compliment it's other memory.

I'm considering testing this out - an AI memory system that seems well thought out, and tops benchmarks. And it's free. Looks like the real deal for anyone running agentic workflows. Worth a look if memory is your bottleneck. I asked my agent (Hermes Agent) if it's possible to work with and it said 'absolutely, as it's an mcp server and I'm an mcp client etc' - but did suggest I add skills/cron to handle the proactive search components. What is the consensus for S-tier Hermes Agent memory ? Reference: github.com/MemPalace/memp…