🚨 JUST IN 🚨
Announcing the @NousResearch Hermes adapter for @Alibaba_Qwen Qwen3.8-27B!
Much more efficient and accurate agentic development with Qwen3.8-27B + Hermes!
- SWE-Bench Pro (hard 51) pass@1: 29.4% → 43.1% | with xhigh thinking: 45.1% → 51.0%
- Terminal-Bench 2.1 pass@1: 44.7% → 58.8% | with xhigh thinking: 58.8% → 57.6%
With thinking off, it matches the base model thinking at xhigh, while using 3.5-4.4x fewer tokens
huggingface.co/harness-hub/Q…
Krethys retweeted
We've partnered with @Microsoft to bring Hermes Agent to the enterprise.
Hermes Enterprise now works inside Microsoft Teams, the Microsoft Store and Azure. In Teams, employees hand Hermes work like financial analysis, document drafts or inbox triage, and review the result in the same chat. Agent workloads run in isolated Azure Container Apps sandboxes.
When someone finds a good way to do a recurring task, Hermes saves it as a skill. With Collective Wisdom, they can share that skill with their team after review, so the next person starts out with the best approach anyone has found to accomplish that task. The skills then grow along with the company.
Companies with strict data residency or procurement rules can run Hermes Enterprise in their own Azure tenant. Our CTO Jeffrey Quesnelle presents how Hermes uses these sandboxes at Microsoft Ignite today, in session BRK448.
Thanks to @M12vc and the @Azure Container Apps team.
nousresearch.com/hermes-ente…
Krethys retweeted
🔴 CRITICAL · Ubiquiti UniFi Access Application: 5 new CVEs
Worst (9.9): root code execution via symlink following in file access (CVE-2026-132802)
👉 Fix: 4.3.24
cve.now/CVE-2026-132802?rele…
Krethys retweeted
🔴 CRITICAL · Incus: 8 new CVEs
Worst (10.0): auth bypass in TLS client certificate chain validation (CVE-2026-130778)
👉 Fix: 7.6.0
cve.now/CVE-2026-130778?rele…
one line to install it:
> `hermes plugins install adaption`
three skills come with it: one to prepare a dataset, one to generate a dataset from a description, one to launch and follow a fine-tuning run.
you sign in once with your Adaption account, and Hermes Agent asks before each import, dataset generation or training run.
enjoy!
Krethys retweeted
Critical Zero-Day Vulnerability in Citrix NetScaler RCE blog.securelayer7.net/cve-20…
Krethys retweeted
🔴 CRITICAL 9.9 · Oracle Database: full takeover of Oracle Text over the network (CVE-2026-114848)
Any user with basic login rights can take over Oracle Text remotely and affect other products.
👉 See vendor advisory
cve.now/CVE-2026-114848?utm_…
Krethys retweeted
‼️ BREAKING: A 10-year-old flaw in #NGINX could let attackers execute code on servers — no login required.
Dubbed #nginx2root (CVE-2026-123007), the critical HTTP/2 vulnerability scores 9.2/10.
Public PoC available. Patches released.
Full details ↓ thehackernews.com/2026/11/10…
Krethys retweeted
⚠️ EARLY WARNING · Microsoft: Google reports stolen cloud data used to breach two unnamed US organizations
Reported by The Record.
👉 If you use Microsoft: Review administrator accounts and third-party app access in cloud tenants.
cve.now/SZB-b7d3842da9?utm_s…
Krethys retweeted
The watchTowr team is currently rapidly reacting to the newly published "NGINX2root" Remote Code Execution vulnerabilities, including CVE-2026-123633 and others in NGINX's HTTP/2 handling.
Active watchTowr Platform clients are being made aware of their exposure.
Krethys retweeted
24 hours left to submit your plugin. We've received hundreds of awesome submissions and the judges are excited to review them all!
The Hermes Agent Plugin Hackathon starts now!
It runs for 7 days, with $20,000 in cash prizes and more.
Plugins are the most powerful way to extend Hermes Agent, and we want this hackathon to show what they can do. A plugin can change anything from the model Hermes runs on, where it stores its memory, where it runs commands, which messaging apps it works in and what Hermes Desktop shows. Plugins in the marketplace already let Hermes do things like control a phone or turn a photo into a printable 3D model.
Every kind of plugin is eligible, so build whatever functionality you want Hermes to have. We'll list accepted entries in the new Hermes Marketplace, where every Hermes user can install them.
Prizes
1st: $10,000 + neon sign + merch + $1,000 creds
2nd: $5,000 + neon sign + merch + $1,000 creds
3rd: $2,500 + neon sign + merch + $1,000 creds
4th: $1,500 + merch + $500 creds
5th: $1,000 + merch + $500 creds
Runners up (x5): merch + $250 creds
Submissions are due 5PM EST on Nov 11th. To enter:
1. Open a pull request that adds your plugin to the Hermes plugin catalog: hermes-agent.nousresearch.co…
2. Post a demo video on X and tag @NousResearch
3. Submit both links through the form: form.typeform.com/to/FwJLvOl…
Your entry is the plugin itself. Judges score it on usefulness, reliability, polish and creativity, and they favor plugins that do more than a prompt or a skill could. Keep the demo under 90 seconds and show the plugin working.
The developer guide shows how to build and test a plugin: hermes-agent.nousresearch.co…
When submissions close, we'll open a thread for every entry in the Nous Research Discord, so you can browse all the plugins and talk to the people who built them.
You can submit the form as soon as your pull request is open. The catalog checks run once a maintainer starts them, and we review entries every few days.
If you have any questions stop by the Nous Research Discord: discord.gg/nousresearch
GLHF!
Krethys retweeted
Hermes is exploding right now.
1,300+ plugins. 100K skills. New releases all the time.
Keeping up shouldn't be a full-time job. hermeswatcher.com puts all of it in one place. No account needed.
Here's what's on it 👇
Krethys retweeted
Asking Hermes for the same thing twice? That's a skill waiting to happen.
Why it pays off:
▸ You stop re-explaining. Write it once, reuse it forever.
▸ Same result every time. Your format, your order, your standards.
▸ Fewer misses. The steps run in the right order, and the mistakes you already hit get written in so they don't come back.
▸ Faster tasks. Hermes starts from the plan instead of working it out from scratch.
▸ No cost until it's needed. Hermes only reads the name until a task calls for it.
What to turn into skills:
▸ your weekly report, in your format
▸ writing posts in your voice
▸ cleaning up a messy spreadsheet the same way every time
▸ researching a topic and summarizing it your way
How: just tell Hermes "turn that into a skill." It writes the steps down once and follows them every time after.
Each skill also becomes its own slash command, and sometimes Hermes saves one on its own after working out a tricky workflow.
Explain it once. Never again.
Krethys retweeted
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
Hermes Agent v0.23 was just released!
The biggest headline new feature is that you can now host the desktop app as a webapp!
Access your agent over your web browser from anywhere.
See the full release notes below!
Krethys retweeted
Hermes Agent v0.23.0: The Hearth Release
Highlights:
- Desktop in a browser tab
- One gateway for every conversation
- /Rewind
- Group Chats with automatic routing
- Spend limits for paid tools
- Lighter and faster
and more
Changelog below
Thanks for being part of our developer community all!
I can't believe this happened. This is AMAZING !!🚀
GitHub's Octoverse 2026 ranks 𝗛𝗲𝗿𝗺𝗲𝘀 Agent #1 most-engaged among single-vendor open source, and stars are only one third of that score 🏆
Octoverse is GitHub's yearly report on what people build and use on GitHub. "Most engaged" means lots of people are actively using a project, not just bookmarking it.
Kudos Team @NousResearch and @Teknium
GitHub blends 3 rankings:
🔹 Stars
🔹 Forks
🔹 Distinct people opening PRs and issues
Why it matters: more people filing clear bug reports means problems get found and fixed faster.
Window: Oct 1, 2025 to Sep 30, 2026. opencode and Earendil's pi are on the same list. OpenClaw tops the community side.
That third signal is you. Every clear bug report counts:
github.com/NousResearch/herm…
How to file a good one: run hermes debug share and paste the links. Add --local to review the report first.
Limit: the ranking measures activity, not quality.
Have you filed a 𝗛𝗲𝗿𝗺𝗲𝘀 issue yet?
Krethys retweeted
October in a nutshell:
- PHP got hacked
- Railway got hacked
- OpenCode got hacked
- Binance got hacked
- Polymarket got hacked
- GitHub Actions got hacked
- SoftBank got hacked
- Cursor marketplace got hacked
- Coinbase vendor got hacked
- Fireworks AI got hacked
- LiteLLM got hacked
- Capcom got hacked
- npm packages got hacked
- TiDB Cloud got hacked
- Warp's vendor got hacked
happy cybersecurity awareness month


















