Blog Divinci AI

Perspectives, mises à jour et leadership éclairé sur l'intelligence artificielle, les systèmes RAG et la gestion de l'IA d'entreprise.

Engineering

Hosted Hermes on Cloudflare: One Agent, One Sandbox

Par Mike Mooring • July 17, 2026

We now host NousResearch Hermes agents inside Divinci — one isolated Cloudflare Sandbox container per agent, chattable in-app or connectable from a local Hermes over an OpenAI-compatible proxy. Here's what it is, who it's for, and how the isolation and security actually work.

Lire l'article

Blog Divinci AI

Hosted Hermes on Cloudflare: One Agent, One Sandbox

Articles récents

WWW-RAG: Making the Open Web Chattable, From One MacBook to Cloudflare

Prominence Is Not Relevance: Teaching a Storefront Assistant What to Recommend

We Made Our RAG Pipeline Parse PDFs 20–50× Faster

We Tested Headroom Against Our EXIT RAG Compressor

Automated LLM CI/CD Pipelines With Instant Rollback

Validating and Releasing Custom LMs in Regulated Fields

The 12 QA + Release Capabilities Every Custom-LLM Platform Ships

10 CI/CD Release Failures in Custom LMs — Which Stage Catches Each

CI Testing for Custom Language Models in 2026

Blog Divinci AI

Hosted Hermes on Cloudflare: One Agent, One Sandbox

Articles récents

WWW-RAG: Making the Open Web Chattable, From One MacBook to Cloudflare

Prominence Is Not Relevance: Teaching a Storefront Assistant What to Recommend

We Made Our RAG Pipeline Parse PDFs 20–50× Faster

We Tested Headroom Against Our EXIT RAG Compressor

Automated LLM CI/CD Pipelines With Instant Rollback

Validating and Releasing Custom LMs in Regulated Fields

The 12 QA + Release Capabilities Every Custom-LLM Platform Ships

10 CI/CD Release Failures in Custom LMs — Which Stage Catches Each

CI Testing for Custom Language Models in 2026

Partager avec des amis