Skip to content
Back to the index

cmd-guard

PyPIInfrastructure

PulseGate's liveness check found it on 19 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 19 Sep 2026. How this is checked

cmd-guard is an open-source command and tool execution guard for AI agents, distributed as a Python package. It provides type-safe policy enforcement for Claude Code hooks and other agent tool-execution workflows.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
1star
5features
2026since

Overview

5 features

Purpose: Preventing unsafe or unauthorized tool execution by AI coding agents.

Inferred · not functionally tested

Audience: developers building or securing AI coding agents

Inferred · not functionally tested

Functions: agents, monitoring

Inferred · not functionally tested

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

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the AI security & guardrails space, cmd-guard takes a focused approach. Inferred · not functionally tested: It focuses on preventing unsafe or unauthorized tool execution by AI coding agents. Inferred · not functionally tested: It is built as an open-source project for developers building or securing AI coding agents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: cmd-guard is available on the command line, and it can be self-hosted.

NieXi builds and maintains cmd-guard, and it first shipped in 2026. The project is developed in the open on GitHub with 14 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include tool execution guards, Claude Code hooks, and type-safe policies.

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

Tasks: Inferred · not functionally tested

  • Tool execution guards
  • Claude Code hooks
  • Type-safe policies
  • Agent security
  • Command validation

Topics: Inferred · not functionally tested

Tags
ai-agent-securityclaude-code-hookstool-execution-guardtype-safe-policy-enforcement
AI capabilities
Code
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Written with
Claude Code
Runs on
CLISelf-hosted
Written with — evidence
Claude Code
commit 520298baee90 · since Sep 2026

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHub · ★ 1Active maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed18 Sep · 07:54 UTC
    cmd-guard seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about cmd-guard

What is cmd-guard?
Inferred · not functionally tested: Cmd-guard focuses on preventing unsafe or unauthorized tool execution by AI coding agents. It is catalogued under AI security & guardrails on PulseGate.
Who is cmd-guard for?
Inferred · not functionally tested: cmd-guard is an open-source project built for developers building or securing AI coding agents.
Does cmd-guard have a free plan?
Basis unknown · not verified: Yes — cmd-guard is open source under the MIT license and free to use.
What platforms does cmd-guard run on?
Basis unknown · not verified: cmd-guard runs on the command line. It can also be self-hosted.
Is cmd-guard still maintained?
PulseGate's liveness check found it on 19 Sep 2026. Its GitHub repository shows 14 commits in the last 90 days.
What are alternatives to cmd-guard?
Similar projects tracked by PulseGate include AgentGuard CLI, combra-guard, and agent-memory-guard.AgentGuard CLIcombra-guardagent-memory-guard
Who develops cmd-guard?
cmd-guard is developed by NieXi.
When did cmd-guard launch?
cmd-guard first shipped in 2026.

Similar projects

Closest matches by what these projects do