Product page · Safe Mode for coding agents

Route risky
actions before they
run.

Safe Mode gives AI coding agents a controlled path for file writes, command-like tools, Git mutations, package changes, and deploy-like actions when those actions are routed through AgentVeil.

Configured routes only. Not host-wide sandboxing. No claim of complete agent safety.

Codex action-control democonfigured route only
Guided action path

Don't just stop the agent. Give it the next controlled move.

AgentVeil turns a risky routed request into a bounded correction path, then records what actually happened.

Routed requestObserve
Risk + targetClassify
Bounded next actionRedirect
Decision + outcomeProve

AGENTS.md is not a control boundary. It tells the agent what it should do. AgentVeil applies authority when the action reaches a configured route.

Action lab

Click a risky action. Watch the boundary answer.

This is the product idea in one interaction: the agent proposes an action; AgentVeil gives the next safe move on the routed path.

REDIRECTgit mutation

Open a pull request instead.

Project rules can say “do not push directly to main.” On a configured Git route, Safe Mode redirects that request to a pull request before upstream changes.

action: git_push decision: redirect_required next: create pull request evidence: bounded local record
What gets gated

The first useful surfaces for coding agents.

Keep the copy honest: these are controlled when they are routed through AgentVeil, not when they happen through raw shell or unmanaged APIs.

Filesystem

Gate routed writes, deletes, sensitive paths, instruction-file changes, and write-then-execute patterns.

write_file · delete · chmod

Command-like tools

Require approval for routed command tools and block dangerous patterns before execution.

rm · curl | sh · chmod +x

Git

Gate routed Git mutations such as add, commit, reset, clean, rebase, and push on a configured repository.

git push · reset · clean

Packages

Require approval for routed package-manager mutations such as install, update, uninstall, and install-script execution.

npm install · pip install

Release / CI

Review routed release, workflow, package-publish, and deploy-like actions exposed through a configured path.

workflow · release · deploy

MCP and connectors

Bring supported MCP and connector actions through one policy boundary where connected.

MCP · IDE route · API gate
Boundary Doctor

Show what is controlled, missing, or bypassable.

Project instructions express intent. Doctor shows whether authority actually exists on the configured route, and exposes raw shell or direct access as bypass risk.

MCP tool pathrouted
Approval centerrunning
Local proofobserved
Package routeconfigured
Raw shellbypass risk
Direct credentialsbypass risk
Deploy routenot configured
Host-wide controlnot claimed
Connect your coding agent

Add the controlled route to the terminal you already use.

Choose a supported client, connect one project, then use Doctor to confirm what is routed before the agent acts.

Cursor
Plans

Delegate actions without handing over control.

Start locally. Add hosted records and team-scoped controls when agents move closer to code, credentials, and sensitive systems.

CORE

Core

$0 forever

Open-source control layer for AI-agent workflows.

  • Open-source AgentVeil CLI
  • Local approval loop
  • Basic redirect guidance
  • Local evidence and status
  • Public fallback path
  • No license required
Install Core
TEAM

Team

$399 / month

For teams controlling agent actions across shared development workflows.

  • Shared workspace and team policy controls
  • Team approval routing
  • Shared action history and decision records
  • 90-day shared record retention
  • 300,000 routed action decisions / month
  • Development workflow controls
Request Team Access
ENTERPRISE

Enterprise

Contact us

For organizations with custom security, deployment, and compliance requirements.

  • Custom controlled-action volume
  • SSO / SCIM options
  • Custom retention and legal hold
  • Security review
  • Private deployment options
  • Custom support and SLA terms
Talk to us

Monthly allowances are based on routed action checks: agent actions evaluated by AgentVeil before execution. Routine checks can allow actions automatically; higher-risk checks can require approval, block, or redirect. Local-only Core usage is free.