Two products, one rule library

AgentTrail Guard vs AgentTrail OS

AgentTrail Guard protects your machine. AgentTrail OS protects it and keeps the record, free for one developer and ready for a team. Both block the same dangerous actions from the same open rule library. What differs is where the decision is made, what is kept, and what you can show afterwards.

AgentTrail GuardAgentTrail OS
Who it is for, and where it runs
In a sentence
AgentTrail Guard: A seatbelt for your coding agent
AgentTrail OS: Guardrails and a record for your agents, solo or as a team
Protects
AgentTrail Guard: One developer, one machine
AgentTrail OS: One developer, or a whole teamFree is one seat. Add teammates on Team.
Agents
AgentTrail Guard: Claude CodeCursorCodex CLI
AgentTrail OS: Claude CodeCursorEnforcement on Cursor requires Cursor 3.21.16 or later.
Setup
AgentTrail Guard: One npm install, then one init command per agent
AgentTrail OS: Sign up, then connect your agent with the AgentTrail CLI
Account and network
AgentTrail Guard: NoneNo network calls, no telemetry, no install ping. Crash reports are opt-in and off by default.
AgentTrail OS: YesAn account, and your agents' high-risk actions are evaluated against your organization's policies.
Price
AgentTrail Guard: FreeApache 2.0, commercial use included.
AgentTrail OS: Free · Team $25 · Business $65Per seat, per month. Enterprise is custom.
Metering
AgentTrail Guard: Never
AgentTrail OS: Governed actions onlyHigh-risk actions count against a generous allowance. Ordinary agent work is never metered.
How a decision is made
Verdicts
AgentTrail Guard: BlockAskWarn
AgentTrail OS: BlockWarnHold for in-app approval
Where the decision is made
AgentTrail Guard: On your laptop, from a catalog bundled into the package
AgentTrail OS: On AgentTrail's servers, from your organization's policies
When something breaks
AgentTrail Guard: Fails openThe call proceeds, and is noted as not checked.
AgentTrail OS: Fails closedThe action does not proceed.
An “ask” rule
AgentTrail Guard: Your agent's own prompt, answered on the spot
AgentTrail OS: A hold in the approval queue, resolved in the app
Rules, history and proof
Your own rules
AgentTrail Guard: A local JSON file
AgentTrail OS: Authored in the appIncluded on Free.
History
AgentTrail Guard: A local log on your machine, capped and clearable
AgentTrail OS: Full session observability, searchable
Learning
AgentTrail Guard: A one-off scan of past transcripts into a local report
AgentTrail OS: Repeat-failure patterns captured automatically and turned into rules
Proof
AgentTrail Guard: Not applicable
AgentTrail OS: Policy backtesting: prove a rule on your history before enforcing itPro
Team
AgentTrail Guard: Nothing syncs, nothing is shared
AgentTrail OS: Team-wide, synced enforcementTeam
Oversight
AgentTrail Guard: Not applicable
AgentTrail OS: Approval queue with response-time tracking, and an audit trail with exportBusiness
Neither product enforces harder than the other. The rule content and the verdicts are identical; these are the honest differences.

Which one is for you?

AgentTrail Guard is the fastest start. AgentTrail OS is free for one developer too, and it is where your agents' history, patterns and proof live.

AgentTrail GuardApache 2.0

Choose AgentTrail Guard if…

  • You want protection in the next minute, with no sign-up.
  • Nothing may leave your machine, whether air-gapped, locked down or on principle.
  • You want to read every rule, and every line of the tool that enforces them.
  • You are new to agentic coding and want a seatbelt before anything else.

Your agent is stopped before it runs terraform destroy, rm -rf $VAR or reads your .env. Free, local, no account.

Install AgentTrail Guard
AgentTrail OSFree plan

Choose AgentTrail OS if…

  • You want every agent session on the record and searchable, not a capped log on one laptop.
  • You want the product to find the mistakes your agents repeat and propose the rule.
  • A second person uses coding agents, and every machine needs the same rules, proven on your own history first.
  • Someone asks “how do you govern your AI agents?” and you need an answer with a record behind it.

Start free on your own: the same protection, plus a searchable record and rules grounded in your own history. Add your team when it is time.

Start free with AgentTrail OS

Moving from AgentTrail Guard to AgentTrail OS

You don't uninstall anything. AgentTrail OS takes over project by project, and AgentTrail Guard keeps protecting the rest.

  1. 1

    Run setup in the project

    npx -y @agenttrail/cli@latest setup --agent claude in each project you want AgentTrail OS to decide in. Setup checks that your AgentTrail Guard can stand down; if it can't, setup stops before writing anything and tells you how to update it.

  2. 2

    AgentTrail Guard stands down there, and only there

    After AgentTrail OS enforcement is verified, setup records the project on this machine, and AgentTrail Guard steps aside in it. It keeps protecting every other project. If it can't confirm that AgentTrail OS is the one deciding (another server, another credential, the plugin turned off), it keeps enforcing, so you may see two prompts, never none.

  3. 3

    See what your organization doesn't enforce yet

    Before AgentTrail Guard stands down, setup lists the rules it enforces that your organization doesn't: your own rules, library rules your organization turned off, and stricter actions. It asks first, and won't stand AgentTrail Guard down at all for an organization with no enabled policies.

  4. 4

    Carry your settings over

    Setup writes guard-import.json on your machine and prints its SHA-256. In the app, Governance → Import from Guard reads it in your browser, shows every change in full, and applies only the ones you tick: library rules your organization is missing or turned off, stricter actions as personal copies, and your own rules if you opt in. Changes to rules everyone shares need an Admin.

What changes once AgentTrail OS decides

When AgentTrail can't be reached
Your organization's fail mode decides, closed by default: the action is blocked, and your agent says why. AgentTrail Guard lets the action through. Setup and the import screen tell you which way it changes for you.
An “ask” rule
Becomes a hold in the approval queue, for up to the rule's timeout (at most 590 seconds). If nobody answers, the decision comes back to you; a headless run is blocked.
Your permissions.allow rules
Can't skip an approval while a reviewer can still answer it. After the window, the decision comes back to Claude Code, where an allow rule applies as before.
If the decision server refuses to answer
The hook gives no decision, and Claude Code's own permission flow decides. This is a defensive path for an unexpected refusal, not a plan limit.
What doesn't carry over
Your allowlist (AgentTrail has no per-pattern exemption, so change the policy on purpose), any action you made weaker than your organization's, and AgentTrail Guard's own decision log. Your AgentTrail Guard files stay on disk, unread in projects AgentTrail OS decides.
Cursor
AgentTrail Guard can't stand down in Cursor yet, so setup stops while its Cursor hooks are installed. Remove them first with npx -y @agenttrail/guard@latest uninstall --agent cursor.

Start with AgentTrail Guard. Sign up free for AgentTrail OS when you want a record.

  1. 1

    Protect yourself

    AgentTrail Guard. Free, open source, on your machine.

  2. 2

    Remember

    A free AgentTrail OS account, still just you: every session searchable, repeat failures captured, your own rules managed from a screen.

  3. 3

    Protect the team

    Team: enforcement synced to everyone, each rule backtested on your own history first.

  4. 4

    Oversee

    Business: the approval queue with response-time tracking, and an audit trail with export.

“AgentTrail Guard already blocks it. Why sign up?”

AgentTrail Guard blocks the bad action on one machine, with rules you maintain by hand. AgentTrail OS, free for one developer, keeps every session searchable and turns the mistakes your agents repeat into rules. On Team, those rules sync to everyone, proven on your history before you enable them. Approvals and an audit trail sit on top.

AgentTrail Guard stops the mistake. AgentTrail OS remembers it and turns it into a rule.