Loading...

Nous Research is bringing its open-source Hermes Agent directly into Microsoft Teams, promising to turn individual prompt tricks into automated workflows for the whole office. With a new feature called "Collective Wisdom," the agent automatically converts successful tasks into reusable code-based skills that team members can review and share across their workspace.
As reported by The Decoder, companies will soon be able to deploy Nous Research's open-source Hermes Agent straight inside Microsoft Teams, alongside a desktop app available in the Microsoft Store. According to Nous Research, employees can hand off everyday chores like document drafting, financial analysis, or inbox sorting to Hermes and review the output directly within their Teams chat.
To handle security, the agents run inside Azure Container Apps Sandboxes using isolated microVMs. The Decoder notes that Hermes automatically packages successful workflows into reusable skills consisting of a description and executable code. Through the "Collective Wisdom" feature, team members can review and share these custom skills with colleagues, keeping the underlying business knowledge contained within the company rather than feeding it back into AI model training data.
Nous Research, which sits in Microsoft’s M12 venture capital portfolio, claims Hermes Agent is currently the most widely used open agent on OpenRouter, handling nearly two trillion tokens daily. The Decoder points out that Microsoft is playing multiple sides of the open-source agent space, having backed competing local agent OpenClaw for Windows PCs earlier this year.
If you run a small team, you already know the prompt engineering bottleneck: one tech-savvy employee figures out a brilliant way to parse invoices or summarize client calls, but that knowledge lives trapped in their private chat history. Most company "prompt libraries" end up as forgotten documents full of outdated copy-paste text.
Hermes Agent's approach to capturing workflows as structured, reusable code skills inside Microsoft Teams could solve that tribal knowledge leak. For small companies that already live inside Microsoft's ecosystem, having an agent operate within isolated Azure microVMs provides real data privacy without needing a dedicated DevOps engineer to configure local sandboxes. Still, open-source agent execution in team chats can quickly become noisy if permissions aren't tight. The real test for small business leads won't be whether Hermes can turn a workflow into code, but how easily non-technical managers can review and approve those shared skills before they get distributed company-wide.
OpenAI's internal data shows researchers value their AI coding agents so highly they'd rather give up staff, despite the tools frequently producing 'AI slop' and requiring significant human oversight.

Reson8 open-sourced Rumble-2-Flash, a 0.5B parameter ASR model for 40+ languages that outperforms models up to 60x larger, with Apache 2.0 licensing.

Instagram introduces a tool to detect unauthorized video reposts and AI-modified content, allowing creators to block or label infringing posts.

Google Maps’ new Ask Maps AI can auto‑create day‑by‑day itineraries, share them, and even call businesses for appointments—useful for small teams on the move.

Comments2
Interesting approach—turning ad‑hoc prompts into a library of repeatable skills could become a hidden lead‑gen engine if you surface the output to your CRM or outreach tools. Have you seen any early metrics on adoption speed and what governance model works best to keep the shared code base clean?
I’ve seen the pilot logs – teams start dropping new Hermes skills within a day or two, but the churn spikes unless you enforce a simple pull‑request workflow and a weekly “skill‑clean‑up” sprint; a lightweight guild model beats a top‑down admin lock for keeping the repo tidy.
The auto‑harvesting of prompt tricks into reusable code is a solid bridge between solo bots and maintainable RPA libraries, but I’m curious how Hermes handles versioning and governance as those skills evolve across teams. In practice, seamless integration with existing orchestration tools like Power Automate or UiPath will be the real test for enterprise adoption.