Skip to content
guardanaPublic

About

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gateway today; connected-channel supervision and scoped reactions toward 1.0. Experimental alpha.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

12 stars

Watchers

1 watching

Forks

Latest commit

 

History

388 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Guardana Control

Decide what your AI agents run. Check what they did.

Guardana Control puts your rules between an AI agent and its tools. Each call that goes through it is allowed, blocked or held for a person before it runs.

CI Security OpenSSF Scorecard OpenSSF Best Practices Release Go 1.27 License: Apache 2.0 Status: alpha

Website · Try the demo · Docs · Status · Roadmap · Contributing · Security

What you can do today

  • Put the gateway in front of an MCP server and decide each tool call from a signed policy before it runs (experimental).
  • Hold a risky call for a person. An approval covers one exact call, expires and works once (implemented).
  • Let the authorization service you already run veto calls over AuthZEN. It can refuse a call and never widen what your policy allows (experimental).
  • Let a tool of your own ask before it acts, through the enforcement API or a coding agent's hooks. Your client enforces the answer (experimental).
  • Check a recorded run against its procedure, and stop that run's later calls, or under signed authority its agent's or principal's, through a signed route (experimental).
  • Read each decision with the policy version that made it, and see in the coverage map which paths nobody observed (experimental).

Status is the one inventory of what exists.

Try the demo

The demo needs no Go and no model key. On Linux or macOS:

  1. From the latest release, download guardana-control-demo_<version>_<os>_<arch>.tar.gz, check it as RELEASING.md shows, extract it and enter its directory.

  2. Start the gateway in front of the demo's two servers:

    bin/guardana-gateway dev --decision-point=silent \
      --config examples/vulnerable-mcp-agent/demo.yaml \
      --policy examples/vulnerable-mcp-agent/policy.json
    
  3. In a second terminal, set MCP to the mcp address it printed and call the tools as an agent would:

    examples/vulnerable-mcp-agent/call.sh "$MCP" read_order '{"id":"ord-1"}'
    examples/vulnerable-mcp-agent/call.sh "$MCP" refund '{"id":"ord-1","amount":"500.00"}'
    examples/vulnerable-mcp-agent/call.sh "$MCP" update_order '{"id":"ord-1","status":"cancelled"}'
    

    The read runs, the refund is blocked, and the update waits for a person. Approve it with the approve_command the gateway printed, then send the same call again: it runs once.

The tutorial does the same with the trail of those calls, and its follow-up goes on with a pause, the counters and the demo's scenarios.

How to use it

guardana-gateway run --config <file>
guardana-control policy test <dir>
guardana-control policy sign --key <file> --out <file> <document>
guardana-control supervise --procedure <file> --runs <dir> --run <run-id> --findings <dir>

Each release has archives of both binaries for Linux and macOS on amd64 and arm64, with a signed checksums.txt. With Go 1.27.4 or later:

go install github.com/guardana/control/cmd/guardana-gateway@latest
go install github.com/guardana/control/cmd/guardana-control@latest

What it is not

It is an AI agent supervision framework in alpha, not a security boundary: do not deploy it as one. It decides only the calls that go through it. The caller's identity is configured, not logged in. The evidence trail is checked for order, not yet for tampering (planned, B29). Supervision runs when you start it, and a stop refuses later calls without undoing what already ran. No model grants authority, and prompt and tool content capture is off by default.

Related project: Guardana

Guardana verifies AI systems before and after deployment. Control decides and checks what agents do while they run. The projects are independent.

Governance · Decision records · Code of conduct · Trademarks

About

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gateway today; connected-channel supervision and scoped reactions toward 1.0. Experimental alpha.

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

12 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages