Claude, with the whole story.

Pick up the latest company decisions, their sources and the work your other agents left behind.

Install in Claude
Claude
Share
Lobu ChatGPT was working on the Acme rollout. Pick up where it left off, show me the original customer evidence behind its decision, then ask our pricing agent to check the exception and leave the result for Codex to continue.
✣
Picked up the shared handoffShared workspace · From ChatGPT
The previous agent recommended a two-week rollout for Acme, owned by Maya Chen, with the enterprise pricing exception reviewed before launch.
Read the customer evidence3 original sources
Three customer conversations and the rollout brief support the decision. The strongest concern came from Acme's procurement thread.
Asked the pricing agentSpecialist agent · Different model
The pricing agent confirmed the exception stays inside the approved enterprise band and flagged the annual-commitment condition.

Three customer conversations and the rollout brief support the decision. The strongest concern came from Acme's procurement thread.

The pricing agent confirmed the exception stays inside the approved enterprise band and flagged the annual-commitment condition.

I left the verified decision, evidence, and pricing condition in Lobu for Codex to continue from.

1 · Agent handoff2 · Acme procurement3 · Rollout brief
Reply to Claude…
Lobu
Sonnet

Claude can make mistakes. Please double-check responses.

The context is already there.

Lobu syncs your connected sources in the background. Search the live company model with its records, relationships and source events together.

How memory works

Your team's agents, too.

Claude can call shared organization agents with their own skills, identity and permissions. Use paired devices or sandboxed tools where access is granted.

Shared agents and access

Paste this into Claude.

One prompt connects the session. Prefer to wire it yourself? Run the skill installer instead and skip the prompt.

Connect this Claude session to Lobu, the shared company context layer for agents, over MCP: https://lobu.ai/mcp.

Onboard yourself:
- If you have a CLI: register the MCP endpoint above with whatever harness you run (claude mcp add / codex mcp add / pi / opencode), then read the Lobu skill and run search_sdk.
- If you can't touch a terminal: ask the user to open https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Lobu&connectorUrl=https%3A%2F%2Fapp.lobu.ai%2Fmcp to add Lobu with one click, then complete the Lobu sign-in, enable the connector, and choose the workspace — then continue once connected. If the link does not open the dialog, open Settings → Connectors → Add Custom Connector in Claude, paste https://lobu.ai/mcp, and continue the same way.

Authenticate when prompted, then:
Read the Lobu skill at https://app.lobu.ai/api/skill/lobu, then run search_sdk for the smallest SDK surface you need. Do not dump the whole workspace.
Search existing memory before answering or saving a duplicate. Use search_memory/save_memory for durable context, query_sdk for reads, run_sdk for writes. Preview consequential writes first and keep every returned source URL, identifier, and approval status exact — never invent one, never fabricate a returned URL or identifier.
npx skills add lobu-ai/lobu --skill lobu

Add Lobu to Claude.

Connect the MCP server, sign in and choose your workspace. The guide covers your client and self-hosted setup.

Add to Claude
https://lobu.ai/mcp

MCP server · Sign in with your Lobu account