Skip to content
Back to the index

agentsward

PyPIInfrastructure

PulseGate's liveness check found it on 3 Oct 2026; it is registered on PyPI and has been in the index since 10 Aug 2026. How this is checked

agentsward is a developer security tool that lets users approve or deny risky commands issued by AI coding agents from a phone. It supports Claude Code and OpenAI Codex and records an audit trail of command decisions.

Inferred · not functionally tested

PaidCLICloud-managed
Visit PyPI

Overview

5 features

Purpose: Preventing AI coding agents from executing risky commands without human approval and accountability.

Inferred · not functionally tested

Audience: software developers and engineering teams

Inferred · not functionally tested

Functions: agents, monitoring

Inferred · not functionally tested

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

Recorded constraints: pricing: paid · license: Proprietary · platforms: CLI · deployment: cli, cloud_managed

Constraint provenance is unknown; confirm requirements with the publisher.

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

In the AI security & guardrails space, agentsward takes a focused approach. Inferred · not functionally tested: It focuses on preventing AI coding agents from executing risky commands without human approval and accountability. Inferred · not functionally tested: agentsward is a B2B product aimed at software developers and engineering teams. Basis unknown · not verified: Pricing is paid. Basis unknown · not verified: It ships for the command line.

agentsward first shipped in 2026. Inferred · not functionally tested: Key capabilities include command approvals, phone approvals, and audit trail.

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

Tasks: Inferred · not functionally tested

  • Command approvals
  • Phone approvals
  • Audit trail
  • Risky command detection
  • Human-in-the-loop

Topics: Inferred · not functionally tested

Tags
ai-agent-guardrailscommand-approvalhuman-in-the-loopdeveloper-security
AI capabilities
Code
Inference: Cloud API

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
anthropicopenai
Connectors
telegram
Runs on
CLICloud-managed

Trust & compliance

Public signals
HTTPS

Indexing history

2

What PulseGate has recorded for this listing

  1. Indexed10 Aug · 06:46 UTC
    agentsward seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  2. Indexed10 Aug · 06:46 UTC
    agentsward seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open

Frequently asked questions about agentsward

What does agentsward do?
Inferred · not functionally tested: Agentsward focuses on preventing AI coding agents from executing risky commands without human approval and accountability. It is catalogued under AI security & guardrails on PulseGate.
Who should use agentsward?
Inferred · not functionally tested: agentsward is a B2B product built for software developers and engineering teams.
Does agentsward have a free plan?
Basis unknown · not verified: No — agentsward is paid.
What platforms does agentsward run on?
Basis unknown · not verified: agentsward runs on the command line.
Is agentsward still active?
PulseGate's liveness check found it on 3 Oct 2026.
What are alternatives to agentsward?
Similar projects tracked by PulseGate include agent-audit-ledger, warden-ai, and agentack.agent-audit-ledgerwarden-aiagentack
How long has agentsward been around?
agentsward first shipped in 2026.

Similar projects

Closest matches by what these projects do