Skip to content
Back to the index

stack

getstack.runAI security & guardrails

PulseGate's liveness check found it on 8 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 15 Jun 2026. How this is checked

STACK is a runtime control plane for AI agents. It is aimed at situations where agents touch credentials or external services and need controls for signing, routing, auditing, and revocation. The site frames it around the problem that agents can break things quickly when they go wrong.

Inferred · not functionally tested

MITWebCLICloud-managed
stack preview
Visit getstack.run

Overview

5 features

Purpose: Securing and controlling the runtime behavior of AI agents to prevent credential leaks and unauthorized actions.

Inferred · not functionally tested

Audience: AI operations teams

Inferred · not functionally tested

Functions: monitoring, agents

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown

Recorded constraints: pricing: unknown · license: MIT · platforms: CLI, WEB · deployment: browser, cli, cloud_managed

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: getstack.run · github.com. These links do not verify the individual claims.

In the AI security & guardrails space, stack takes a focused approach. Inferred · not functionally tested: It focuses on securing and controlling the runtime behavior of AI agents to prevent credential leaks and unauthorized actions. Inferred · not functionally tested: stack is a B2B product aimed at AI operations teams. Basis unknown · not verified: It runs on the web and the command line.

stack first shipped in 2026. Inferred · not functionally tested: Among its 5 catalogued features are credential proxy, behavioral detectors, and audit logging. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Credential proxy
  • Behavioral detectors
  • Audit logging
  • Global revocation
  • GDPR compliance

Topics: Inferred · not functionally tested

Tags
agent-securityruntime-controlcredential-injection

JSON profile · Text profile · Access guide

Built with & integrations

Framework
Next.js
Hosting
fly
AI providers
anthropic
Connectors
MCPAPI
Runs on
BrowserCLICloud-managed
Detected from
fly
fly-request-id header
Next.js
x-powered-by header · /_next/static/ in the HTML · __next_f in the HTML

Trust & compliance

License
MIT

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about stack

What does stack do?
Inferred · not functionally tested: Stack focuses on securing and controlling the runtime behavior of AI agents to prevent credential leaks and unauthorized actions. It is catalogued under AI security & guardrails on PulseGate.
Who is stack for?
Inferred · not functionally tested: stack is a B2B product built for AI operations teams.
What platforms does stack run on?
Basis unknown · not verified: stack runs on the web and the command line.
Is stack still active?
PulseGate's liveness check found it on 8 Oct 2026.
What projects are similar to stack?
Similar projects tracked by PulseGate include Stackaible, Everstack, and Nanostack.StackaibleEverstackNanostack
When did stack launch?
stack first shipped in 2026.
Is stack open source?
Basis unknown · not verified: stack has a public GitHub repository.
Does stack have an API or integrations?
Inferred · not functionally tested: Yes — stack exposes an MCP server and a public API.

Similar projects

Closest matches by what these projects do