How do Relevance AI agents connect to Glen?

Glen is a standard MCP server. Add it as an MCP tool in your agents, authenticate over OAuth or an API key, and every agent can retrieve org-shared context and write observations.

Does each agent need its own memory store?

No. Glen is org-scoped, so the whole workforce reads and writes one shared store. A fact one agent records is immediately available to the others and to your other MCP clients.

Shared memory for Relevance AI

Relevance AI lets you build an AI workforce, agents and multi-agent teams that run real business processes like research, outreach, and operations, with tools, sub-agents, and triggers. As that workforce grows, the missing piece is a shared brain: each agent and each run tends to operate on the context you hand it, and the durable facts the workforce accumulates about customers, accounts, and processes are hard to keep in one place every agent can see. Glen, shared memory for AI agents, gives your Relevance AI workforce a long-term, org-scoped memory layer over MCP, so every agent reads from and writes to one shared store.

Connect Glen to your Relevance AI agents as an MCP tool and any agent in the workforce can call one tool that both retrieves relevant long-term context and records new facts in a single step. A research agent can pull what the team already knows about an account before it starts; an outreach agent can read that same context and write back what it learned from a reply. You stop passing the same briefing into every agent, and you stop letting each agent's findings stay siloed inside its own run.

Because Glen is org-scoped, the memory is shared across your entire AI workforce and across other tools entirely, rather than bound to one agent or one process. One agent learns a durable fact; another agent on the team, or a human-driven agent in Claude Code or Cursor, reads it next time. That is what turns a collection of agents into a workforce that actually compounds knowledge: persistence that outlives a single run and is shared across the whole team. And because Glen is a standard MCP server, the same memory your Relevance AI agents write is readable from any other MCP client, so your automated workforce and your hands-on tools share one source of truth. You wire it in once over OAuth or an API key and let the memory grow with the work.

FAQ

How do Relevance AI agents connect to Glen?: Glen is a standard MCP server. Add it as an MCP tool in your agents, authenticate over OAuth or an API key, and every agent can retrieve org-shared context and write observations.
Does each agent need its own memory store?: No. Glen is org-scoped, so the whole workforce reads and writes one shared store. A fact one agent records is immediately available to the others and to your other MCP clients.