How is Glen different from Continue's context providers?

Context providers retrieve files and docs into the prompt on demand. Glen persists durable, org-shared knowledge your assistant and team learn, and writes new facts back, not just reads.

Does Continue support MCP?

Yes. Continue supports MCP servers, so adding Glen as a tool is a configuration step, and it works the same way across VS Code and JetBrains.

Shared memory for Continue

Continue is the open-source AI code assistant for VS Code and JetBrains, customizable chat, autocomplete, and agent modes you configure with your own models and context providers. Its context providers pull in files, docs, and snippets on demand, but that is retrieval, not memory: the decisions you make in chat, the conventions you correct, the project knowledge that should accumulate over time, none of that persists across sessions or flows to your teammates. Glen, shared memory for AI agents, gives Continue long-term shared memory as a single MCP tool, so the knowledge your assistant builds up persists and is shared across your whole team.

Continue already supports MCP, so connecting it to Glen is straightforward: your assistant gains one tool that both retrieves relevant long-term context and records new facts in a single round trip. Before it answers or edits, it pulls what your team already knows about this codebase, the patterns, the past decisions, the pitfalls, instead of relying only on whatever context providers happen to surface. As you work, it writes back what was learned so the next session starts ahead.

The distinction is between retrieving content and remembering knowledge. Continue's context providers fetch files and docs into the prompt; Glen persists what your team and its agents actually learn. And because Glen is org-scoped, that memory is shared across every Continue user, every editor, and every other agent in your organization. A decision one teammate's assistant recorded is available to yours next time, and since Glen is a standard MCP server, the same memory is readable from Claude Code, Cursor, or any other MCP client, so the knowledge Continue accumulates feeds your entire toolchain. You connect once over OAuth or an API key and stop losing what your assistant learns at the end of each session.

FAQ

How is Glen different from Continue's context providers?: Context providers retrieve files and docs into the prompt on demand. Glen persists durable, org-shared knowledge your assistant and team learn, and writes new facts back, not just reads.
Does Continue support MCP?: Yes. Continue supports MCP servers, so adding Glen as a tool is a configuration step, and it works the same way across VS Code and JetBrains.