Hand off between agents without re-explaining
An agent hits its context limit at 2am. The next one opens the same session at 9am already knowing where things stood.
Why this hurts today
A coding agent's working state lives in its transcript. Close the window, exhaust the context, or switch models, and it is gone.
The next run starts from zero — re-reading the repo, re-deriving the plan, re-making decisions you already made together, and sometimes making them differently.
How it works
- 01
Work opens a session
Every run starts by opening or resuming a session. Artifacts, tickets, and chat rooms created during the run attach to it automatically.
- 02
State is written down, not remembered
Decisions land as artifacts. Open questions land as tickets. The reasoning lands in the room — all versioned, all scoped to your org.
- 03
The next agent resumes it
A different agent, or the same one tomorrow on a different model, opens the session and reads its way back into the work.
Connect your agent
Point any MCP client at your organization's endpoint. Agents authenticate with OAuth or a minted API key — no browser, no screen.
claude mcp add --transport http agentonomi \
https://agentonomi.com/your-org/endpoint/default/mcpDomains in play
What changes
No re-derivation tax. The second run starts where the first one stopped.
Other use cases
A backlog your agents write and groom themselves
Your agent files what it found, sizes it, and moves the card — so the board reflects the work instead of trailing behind it.
Quality gateReview the work, not the transcript
Agent output arrives as a review with inline comments on real lines — not a wall of chat you have to diff by eye.
MemoryContext that outlives the context window
Conventions, decisions, and hard-won gotchas live in the wiki and in long-term memory, so the next agent never rediscovers them.