Otsoa (@otsoa_d) header
Otsoa (@otsoa_d) profile picture

Founder https://teapaw.org/t.co/ZW1BOYXKUg AI agents · local LLMs · Fine-tuning Deploying Hermes agents from @nousresearch in 🇫🇷 SMEs

Rouen, France
Joined June 2024
Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)Photo by Otsoa (@otsoa_d)
Pinned Tweet
Tenure just landed in the official Hermes marketplace 👀 Your agent gets trust by default, loses it on a mistake, earns it back on proof. Hermes users : what's the first action you'd never let your agent do alone ? Thanks @NousResearch @Teknium @sidbing 🤝
6
1
1
16
1,106
Just discovered the autopilot mode on GTA6 😭 That’s so cool tbh you just have to relax and enjoy the ride with your favorite radio 🔥
3
207
Didn't win with Tenure, but the best reward was meeting so many great people and exchanging ideas throughout this hackathon. Congrats to the winners and to the @NousResearch community ! 🫰 You're the best !
The Hermes Agent Plugin Hackathon winners are here. Thank you to the nearly 1,000 community members who submitted! Agents scored every entry, then five community judges ranked the finalists to pick the top 10. Winners below:
2
1
7
560
Tenure just landed in the official Hermes marketplace 👀 Your agent gets trust by default, loses it on a mistake, earns it back on proof. Hermes users : what's the first action you'd never let your agent do alone ? Thanks @NousResearch @Teknium @sidbing 🤝
1
23
wow, come on, is that true ? we’ll probably get it for free on Hermes for a few days 👀
破案了!! 昨天榜单上的神秘模型Gestalt就是 GLM-5.5!! GLM-5.2 可是在网页设计榜拿过第一,把 Fable 5 都压在了下面 距离 GLM-5.3 发布也已经 三个多月了憋了那么久大招肯定要猛啊 Gestalt 是以G为开头,GLM也是G没有那么多巧合 !!
1
3
453
Nothing is gonna stop me rn
3
2
2
192
7,591
My morning routine on GTA6 is far better than mine irl. 🤷‍♂️
1
92
Did I buy GTA6 to finally play Tenebrae Lux by Johannes Zuch? Absolutely.
1
2
32
1,858
COME ONNNNN 👏👏👏
2
4
155
Ok something crazy is happening right now…
4
172
“ Worst model ever “ Bold claim. Tbh, that’s disrespectful to the people who worked on it 😅
6.2 Astra is here. I’ve been testing it for awhile. I think this is the worst model OpenAI has ever released. I’ll share more soon.
1
3
113
Time to cook for free 👇
To celebrate Mistral Vibe + Le Chonk becoming the world’s best open model-harness duo, we’re making Vibe free in Europe for the first 3 months. (Yes, it’s actually better than GLM / DeepSeek at coding). Use code LECHONK via link in 🧵. Limited time, first-come, first-served.
6
328
You're using Hermes from @NousResearch ? This is the best way to support them! 👇 For just $20, you get: Hermes Agent usage included, with limits that reset daily, weekly, and monthly. A cloud agent with up to 4 GB of RAM and 25 GB of storage included. Access to any model.
13
2
61
9,589
In case anyone wants to give it a try! portal.nousresearch.com/r/ot…
1
555
my agents kept doing stuff i didn't want, and approving everything was killing me. so i built tenure: trust by default, taken back on a mistake, earned back on proof open source, runs locally, no LLM call. claude code version coming would mean a lot if you drop a star ⭐ github.com/otsoa-dubief/tenu…
10
7
311
Qwen4-27B drops in 4 days. 🔥 Your 3090 is about to earn another promotion. Qwen4 27B and Flash fit comfortably in 24GB of VRAM, so a consumer card will start to feel like a data-center node. @Alibaba_Qwen said a week ago that RSI runs through the entire Qwen 4 lineup: Max, Plus, Flash and 27B.
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! 🚀 - Blog: qwen.ai/blog?id=qwen4-max - API: qwencloud.com/models/qwen4-m… - Token Plan: qwencloud.com/pricing/token-… More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
2
170
Thanks @quotumorg 🤝
great list. we indexed all 2,380 Hermes Agent catalog plugins. 492 had a readable author handle, so only those were scored: GitHub activity and X presence, weighted by public replies, quotes and answered mentions. our index, our criteria. #1 plugin is gadget, by @adolandev, who also made Hermes Sheets and Hermes Whiteboard, two of the nine above. next, mayfly: one plugin, a fresh @instabox_sh box, a receipt, then the box is deleted.
1
2
5
193
Everyone's shipping like crazy because we all know GTA 6 drops this week and we're all cooked 😭😭😭
2
146
Sunday, let's connect 🤝 I build AI agents for small businesses and an open-source trust layer for them. If you're into AI, SaaS or building things, say hi below and drop a link 👇
23
12
615
@boardyai bro help me to find new people !
1
61
Loving so much the @NousResearch mobile app with @deepseek_ai. It’s totally a game changer 👏
2
4
158