Skip to content
Back to the index

stopgate

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 24 Jul 2026. How this is checked

Stopgate provides a local-first safety envelope for AI coding agents. It prevents prompt injection, tracks dataflow taint, and adds guardrails so agents can be run unattended. The package is designed for developers building with agents like Claude.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

5 features

Purpose: Running AI coding agents safely without constant human supervision.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: agents, monitoring

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · 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.

stopgate is an AI security & guardrails project. Inferred · not functionally tested: It focuses on running AI coding agents safely without constant human supervision. Inferred · not functionally tested: It is built as an open-source project for developers. Basis unknown · not verified: stopgate is open source under the MIT license. Basis unknown · not verified: stopgate is available on the command line, and it can be self-hosted.

It is developed by Robomba, and it first shipped in 2026. Development happens publicly on GitHub with 22 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include local-first safety, prompt injection prevention, and dataflow tainting. Inferred · not functionally tested: Catalogued interfaces include a public API.

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

Tasks: Inferred · not functionally tested

  • Local-first safety
  • Prompt injection prevention
  • Dataflow tainting
  • Unattended agent execution
  • Guardrails for agents

Topics: Inferred · not functionally tested

Tags
agent-guardrailprompt-injectionlocal-safetycoding-agenttaint-tracking
AI capabilities
Code
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
anthropic
Connectors
API
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed24 Jul · 17:00 UTC
    stopgate seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about stopgate

What does stopgate do?
Inferred · not functionally tested: Stopgate focuses on running AI coding agents safely without constant human supervision. It is catalogued under AI security & guardrails on PulseGate.
Who is stopgate for?
Inferred · not functionally tested: stopgate is an open-source project built for developers.
Is stopgate free?
Basis unknown · not verified: Yes — stopgate is open source under the MIT license and free to use.
What platforms does stopgate run on?
Basis unknown · not verified: stopgate runs on the command line. It can also be self-hosted.
Is stopgate still maintained?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 22 commits in the last 90 days.
Who makes stopgate?
stopgate is developed by Robomba.
When did stopgate launch?
stopgate first shipped in 2026.
Is stopgate open source?
Basis unknown · not verified: Yes — stopgate is open source under the MIT license, developed on GitHub.

Similar projects

Closest matches by what these projects do