
Marrow AI: Control Layer for AI Agents
MCP serverPolicy check before risky agent actions, with proof recorded afterwards
Runs locally- 2 tools
- Freemium
- Security

Policy check before risky agent actions, with proof recorded afterwards
Runs locallyLocal ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action
Runs locallyChecks AI agent actions against your rules and keeps a replayable decision record
Check a user's intent and a proposed agent action against an approved policy
Not checked yetHuman approval desk where AI agents post cards and wait for a person's decision
Not checked yetApproval and budget checks that pause an AI agent before it spends, deploys or sends
Not checked yetGive coding agents your team's architectural decisions and what happened when they shipped
Not checked yetExperimental governance layer that checks, enforces and records what AI agents may do
Gateway that checks agent tool calls against signed grants and records signed receipts
Runs locallyAuthorize AI agent actions before they run, with policy, approval and signed grants
Not checked yetApproval inbox that lets an AI agent propose actions and wait for a human decision
Not checked yet
Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit
Not checked yetThe closest alternatives to Actera are Marrow AI: Control Layer for AI Agents, Abe, Forge AI Accountability, Antaeus and Ayedesk.
Yes. Marrow AI: Control Layer for AI Agents, Abe, Antaeus have a free or open-source option.