Open-source execution governance

Put a decision boundary between AI agents and real tool calls.

ActionProxy evaluates a proposed action, allows bounded calls, denies prohibited calls, queues selected calls for human review, and controls the transition into execution.

Proposed callPolicyAllow · Deny · ReviewControlled execution

Choose the operating path

Start with inspectable software you can run yourself.

OSS focus

ActionProxy Community

Run the approval boundary locally or self-host it, inspect the policy and lifecycle, and keep real-tool credentials in infrastructure you control.

The narrow boundary

Govern the exact action, not the conversation around it.

01

Deterministic policy

Return allow, deny, or require approval from explicit rules over a normalized tool call and trusted context.

02

Bound human review

Connect the reviewer’s decision to the payload, policy, eligibility requirements, nonce, and expiry.

03

Correlatable evidence

Follow the proposal through decision, review, dispatch attempt, and reported outcome without overstating what logs prove.

Current project boundary

Built for local and self-hosted evaluation, with limits stated plainly.

ActionProxy Community v0.1 is a developer preview for local and self-hosted evaluation, not a complete production authorization boundary or hosted SaaS control plane. Real business-tool effects use an external runner or downstream MCP server; the built-in registry is a deterministic demo surface.