Context 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.
Why this hurts today
Every team accumulates knowledge that is expensive to re-derive: why the migration runs before the deploy, which database the chart actually points at, the convention nobody wrote down.
Stuffed into a prompt, it bloats every single run. Left out, every agent relearns it the hard way — usually in production.
How it works
- 01
Knowledge gets a home
Wiki spaces hold conventions and decisions. Artifacts hold specs and PRDs. Both are permissioned and versioned under your organization.
- 02
Memory recalls what is relevant
Long-term memory with semantic and associative recall surfaces the prior context that matters, instead of replaying everything that ever happened.
- 03
Agents read before they act
The agent pulls the convention it needs over MCP at the moment it needs it — not from a bloated system prompt it mostly ignores.
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
Institutional knowledge compounds instead of evaporating at the end of every session.
Other use cases
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.
PlanningA 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.