Click any tag below to further narrow down your results
Links
Nous Research's open-source Hermes Agent is now available inside Microsoft Teams, the Microsoft Store, and Azure, aimed at companies that want a self-improving agent for every employee. The pitch is that successful workflows get saved as reusable skills the whole team can use.
- Hermes Enterprise runs in Microsoft Teams, Hermes Desktop for Windows (via the Microsoft Store), and Azure Container Apps Sandboxes, where agent tasks run in isolated microVMs that start in under a second.
- Hermes turns a successful approach to recurring work into a reusable skill, and a Collective Wisdom feature lets employees review and publish those skills for their team.
- Companies with strict data residency or procurement needs can run Hermes in their own Azure tenant.
This is setup documentation for Ori, a command-line launcher that runs coding agents like Claude Code, Codex, and OpenCode on your OpenRouter account. You sign in once with OAuth instead of managing separate provider keys, and every session inherits your OpenRouter models, credits, and organization guardrails.
- You sign in through OpenRouter with OAuth PKCE, so there's no API key to create or paste, and one login covers every supported agent.
- `ori harness setup` writes OpenRouter settings into each agent's own config so its desktop app and plain command both route through OpenRouter, and `ori harness reset` reverts that.
- Billing and guardrails stay on OpenRouter's side: workspace budgets, allowlists, and ZDR-only routing apply to all traffic, and usage shows up in normal OpenRouter billing with no separate Ori bill.
Microsoft released a narrow model that doesn't generate text. It scores a fixed set of answer options and returns a confidence for each, aimed at routing, classification, and verification in production pipelines. It's built on Alibaba's open-weight Qwen3.5-9B, and most of the performance numbers so far come from Microsoft itself.
- The model returns calibrated probabilities over predefined options in a single forward pass, so applications can act on a score instead of parsing free-form output.
- Microsoft says it beat 36 benchmarks covering about 150,000 questions and runs far faster than GPT-6 Sol on P50 latency, but these are vendor-reported figures with no independent reproduction yet.
- Pricing reported via OpenRouter is $0.042 per million input tokens with free output, and weights aren't released, so access is through hosted APIs only.