Continue research from another assistant
Retrieve a research handoff saved in Claude or ChatGPT. Ask Gemini to examine the open questions using the retained context and its own available tools.
Shared memory for Gemini CLI and Gemini Enterprise. Bring retained knowledge from Claude or ChatGPT into your Gemini workflows with Angareion.
Gemini CLI · administrator-managed Enterprise connector

The direct answer
Angareion connects to Gemini CLI through remote MCP and OAuth, and to Gemini Enterprise through an administrator-configured custom MCP data store. These clients can retrieve authorized context saved in Angareion by other assistants. The consumer Gemini web app and Google AI Studio do not use this connection flow.
Understand shared AI memoryBuilt around your work
Use Gemini for the next perspective on your work, with the background already in reach. Bring forward the facts, sources, and decisions you retained instead of rebuilding the brief in another tool.
Retrieve a research handoff saved in Claude or ChatGPT. Ask Gemini to examine the open questions using the retained context and its own available tools.
Save the useful decisions and discoveries from a CLI session. Retrieve them in a later session or pass a handoff to Codex when the next task belongs there.
An administrator can attach the Angareion connector to a Gemini Enterprise app or agent and choose the enabled actions. Users retrieve only the context their connection is permitted to access.
Inside Angareion
The Connect guide walks you through your client’s setup. Choose the appropriate connection, approve access, and verify the tools before asking for your context.

Your work can travel
Save what matters, then ask another connected assistant to pick it up. The same agent or an authorized shared scope keeps the context available.
“Save the conclusions and open questions from this research in Angareion. Prepare a handoff for Claude to develop the recommendation.”
“Resume the Gemini research handoff. Retrieve the conclusions and help me write a recommendation with the remaining uncertainties clearly stated.”
Illustrative prompts. Your assistant must call the connected tools; chat history and local files are not automatically transferred.
How an AI handoff worksMake the connection
Use Gemini CLI for a self-service connection, or work with your administrator on Gemini Enterprise. Request Angareion access first.
CLI users register the HTTP server and run /mcp auth angareion with a local browser. Enterprise administrators follow the custom MCP data-store guide and request an OAuth Client ID from Angareion support.
Verify the available Angareion tools, then retrieve saved project context. Optional reusable skills are available for Gemini CLI; Enterprise uses the connector without an MCP-backed Angareion Skill.
Questions, answered
What carries over, what needs connecting, and how to keep the work moving.
Explore the knowledge libraryThe supported setup paths are Gemini CLI and Gemini Enterprise. The consumer Gemini web app and Google AI Studio do not use these connector instructions. Choose the appropriate supported surface in the connection guide.
When the Gemini client and selected model can call the configured MCP tools, they can retrieve the same permitted Angareion context. The memory is retained by the agent, not by a Pro or Flash session. Model and tool availability depend on Google’s client and workspace settings.
Yes, after that research has been saved to Angareion and Gemini is connected to the same agent or an authorized shared scope. Ask it to retrieve the memories, find a retained output, or resume a handoff.
An administrator configures the custom MCP data store, authentication, enabled actions, and attachment to the Enterprise app or agent. Use the documented connector path. Angareion currently distributes reusable Gemini skills for CLI, not an MCP-backed Enterprise Skill package.
Retain useful facts and decisions as memories, add reference material to knowledge sources, save complete work products as outputs, and preserve unfinished work as handoffs. These are explicit workflows: Angareion does not automatically record everything you do in every assistant.
Access follows your Angareion agent identity and permitted memory scopes. Reusing the same agent across clients provides continuity; team or institutional sharing requires the appropriate scope and permissions. Connecting a new client does not give it unrestricted access to every memory.
Request Angareion private-beta access, then follow the connection guide for your client. Angareion does not supply the AI client’s subscription or change its account requirements. Compare the current Angareion editions and check the client’s own eligibility before connecting.
Keep what you learn
Request Angareion access, connect Gemini, and build a body of knowledge that can travel with your work.
Private beta. Access is granted from a waitlist.