How do I add Glen to a Flowise flow?

Glen is a standard MCP server, so you add it as an MCP tool node and authenticate over OAuth or an API key. Any agent node in the flow can then call it to read context and write observations.

Does this replace Flowise's memory nodes?

Flowise memory nodes hold one conversation's buffer. Glen adds durable, org-shared long-term memory that persists across flows and deployments and is readable by your other MCP clients too.

Shared memory for Flowise

Flowise lets you build LLM apps and agents visually, dragging nodes for chains, tools, retrievers, and agents onto a canvas and shipping them as chatflows. It has memory nodes for conversation buffers and integrations with vector stores, but durable, cross-flow, cross-deployment knowledge, the facts your flows should accumulate over time and share with each other, is something you wire up and maintain yourself per flow. Glen, shared memory for AI agents, gives your Flowise flows that long-term shared memory as a single MCP tool node, so every chatflow reads from and writes to one org-scoped store instead of each keeping its own.

Add Glen as an MCP tool in your Flowise canvas and any agent node can call one tool that both retrieves relevant long-term context and records new facts in a single step. A flow can pull what your organization already knows about a customer or a task before it answers, and write back what the conversation revealed when it ends. You stop standing up a separate vector store and embedding pipeline just to give a chatflow durable memory, and you stop building per-flow memory silos that never share what they learn.

Because Glen is org-scoped, the memory is shared across every chatflow you build, across staging and production, and across other agents entirely, rather than bound to one flow's memory node. One chatflow learns a durable fact; a different chatflow, even one built by a teammate, reads it next time. That is the part a per-flow conversation buffer does not give you: persistence that outlives the session and is shared across flows and people. And because Glen is a standard MCP server, the same memory your Flowise flows write is readable from Claude Code, Cursor, or any other MCP client, so visual builders and code-driven agents draw on the same knowledge. You connect it once over OAuth or an API key and let the memory compound across your canvas.

FAQ

How do I add Glen to a Flowise flow?: Glen is a standard MCP server, so you add it as an MCP tool node and authenticate over OAuth or an API key. Any agent node in the flow can then call it to read context and write observations.
Does this replace Flowise's memory nodes?: Flowise memory nodes hold one conversation's buffer. Glen adds durable, org-shared long-term memory that persists across flows and deployments and is readable by your other MCP clients too.