Skip to content

Latest commit

 

History

History
48 lines (32 loc) · 1.91 KB

COMPARE.md

File metadata and controls

48 lines (32 loc) · 1.91 KB

Agent Runtime Guard vs other layers

Short positioning for reviewers and list maintainers.

One sentence

Pre-execution, local, fail-closed tool-call interception with offline-verifiable Ed25519 receipts.

Layer map

Layer Typical tools Question answered
Discovery / posture Reco, Pluto, Zenity-class What agents exist and what can they reach?
Config scanners correctover-scan, mcp-guard scanners Is this MCP/agent config risky before it runs?
Egress / proxy firewalls Pipelock, gateway products What leaves the network boundary?
Runtime tool-call guard agent-runtime-guard, HOL Guard-class Can this specific tool call execute now?
Kernel / sandbox eBPF MCP sandboxes Can the process make this syscall?

vs Pipelock-class egress firewalls

Agent Runtime Guard Pipelock-class
Primary surface MCP / tool-call arguments Mediated HTTP, WS, MCP, tunnels
Install npx MCP server Binary / proxy topology
Receipts Ed25519 per decision Mediator-signed action receipts
Best when Agent already has MCP tools attached You control egress path

Complementary: proxy stops bulk exfil on the wire; we stop the bad tool call before it runs.

vs config-only scanners

Scanners find bad configs. We enforce at call time. Use both.

vs discovery platforms

Discovery does not block a single curl|sh. We do not map your SaaS agent estate. Use both.

Public proof assets

Not claims we make

  • Not “blocks 100% of attacks”
  • Not a full SaaS posture platform
  • Not an IETF standard (personal Internet-Draft only)