In building a content index to connect enterprise content to AI agents, Hyland has taken the open-source route — and brought an open-source veteran out of retirement to lead the project.
OpenArch, an open-source content index, connects data repositories built on content management platforms including Alfresco and Nuxeo — which Hyland acquired in 2020 and 2021, respectively — to AI services and agents. It's not an AI harness, but it can be part of an overall harness strategy, said Alan Pelz-Sharpe, founder of independent research firm Deep Analysis.
The index catalogs metadata, permissions, business rules and other signals associated with enterprise content. Those details help govern what AI agents can retrieve and support compliance with corporate and regulatory policies.
"This is a good thing," Pelz-Sharpe said. "Usually, AI just strips the data out of the file and dumps the file, so they've got no history, no security, no permissions, no metadata. [AI tries] to invent its own metadata."
OpenArch is available on GitHub under an Apache 2.0 license.
Open source a tactical move
Hyland CEO Jitesh Ghai tapped John Newton to head up the OpenArch project. A veteran enterprise content management (ECM) executive, he had founded open-source Alfresco in 2005 and left the company after Hyland acquired it in 2020. Before that, he co-founded Documentum, which OpenText later acquired. He rejoined Hyland in 2025 as chief innovation strategist.
His ECM and open source bona fides are helping Hyland's customers move faster into the agentic AI era, Pelz-Sharpe said. The project is also smart marketing, as Hyland's free connectors extend beyond the company's customer ecosystem.
"Hyland gets that open source is a key to unlocking bigger projects," Pelz-Sharpe said. "That's the big deal — you have open source when it comes time to connect. Who wants to buy a connector? Who's going to go out and put out an RFP for a connector? Nobody. It's a really clever way, frankly, of getting traction outside your core user base."
"An agent shouldn't have to care where that content lives; where it lives may inform the agent, but it shouldn't be the agent's problem."
John Newton
chief innovation strategist, Hyland
Newton said that OpenArch was designed to be deployed on-premises or in hyperscaler environments, depending on the user's needs.
AI agents are only as good as the content they can access. Newton said that for many enterprises, content remains scattered across multiple systems — each with its own permissions and rules. The open source format enables developers to deploy OpenArch themselves, connect to the systems that matter to them, see how permissions are handled and keep content and AI inside their own infrastructure when required.
"Most enterprises can't say where a given piece of information lives," Newton said. "It can live in a legacy ECM system. It can be in an operational repository. It can be in a compliance system. It could be in SharePoint or applications like Salesforce and ServiceNow — and each has its own permissions.
"An agent shouldn't have to care where that content lives; where it lives may inform the agent, but it shouldn't be the agent's problem. OpenArch is this layer underneath. It indexes content across the repositories, keeps all the permissions and metadata with it, and gives an agent one place to retrieve the originals."
Don Fluckinger is a seasoned B2B technology journalist with more than 30 years of experience specializing in enterprise IT, digital experience and content management. As a senior news writer at Informa TechTarget, he delivers award-winning analysis that helps IT and business leaders navigate complex technologies to enhance customer and employee experiences. Got a tip? Email him.
