Skip to content
Back to the index

canary-tool

github.comInfrastructure

PulseGate's liveness check found it on 9 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 16 Jun 2026. How this is checked

AI agent watchdog: prompt firewall + filesystem drift detection via IBM Granite.

Inferred · not functionally tested

Open SourceMITWebCLI
canary-tool preview
Visit github.com
1star
4features
2026since

Overview

4 features

Purpose: Protects AI agent workflows by monitoring prompts and detecting unauthorized filesystem changes.

Inferred · not functionally tested

Audience: AI developers

Inferred · not functionally tested

Functions: monitoring

Inferred · not functionally tested

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

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

Constraint provenance is unknown; confirm requirements with the publisher.

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

canary-tool is an AI & LLM security project. Inferred · not functionally tested: It protects AI agent workflows by monitoring prompts and detecting unauthorized filesystem changes. Inferred · not functionally tested: canary-tool is an open-source project aimed at AI developers. Basis unknown · not verified: canary-tool is open source under the MIT license. Basis unknown · not verified: It ships for the web and the command line.

canary-tool first shipped in 2026. The project is developed in the open on GitHub with 21 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include prompt firewall, filesystem drift detection, and AI agent monitoring.

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

Tasks: Inferred · not functionally tested

  • Prompt firewall
  • Filesystem drift detection
  • AI agent monitoring
  • IBM Granite integration

Topics: Inferred · not functionally tested

Tags
prompt-firewalldrift-detectionai-agent-securityfilesystem-monitoring
AI capabilities
Text

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
multiple
Runs on
BrowserCLI

Trust & compliance

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

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about canary-tool

What is canary-tool?
Inferred · not functionally tested: Canary-tool protects AI agent workflows by monitoring prompts and detecting unauthorized filesystem changes. It is catalogued under AI & LLM security on PulseGate.
Who should use canary-tool?
Inferred · not functionally tested: canary-tool is an open-source project built for AI developers.
Is canary-tool free?
Basis unknown · not verified: Yes — canary-tool is open source under the MIT license and free to use.
What platforms does canary-tool run on?
Basis unknown · not verified: canary-tool runs on the web and the command line.
Is canary-tool still maintained?
PulseGate's liveness check found it on 9 Oct 2026. Its GitHub repository shows 21 commits in the last 90 days.
What projects are similar to canary-tool?
Similar projects tracked by PulseGate include chaincanary, Canary, and canarywire.chaincanaryCanarycanarywire
When did canary-tool launch?
canary-tool first shipped in 2026.
Is canary-tool open source?
Basis unknown · not verified: Yes — canary-tool is open source under the MIT license, developed on GitHub.

Similar projects

Closest matches by what these projects do

Submit to the index
Apps, agents and models — free, no signup.