Skip to content
Back to the index

pyrtkai

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

Safe-by-default CLI layer for AI agents — less noise, less risk: no-shell proxy, fail-closed policy, deterministic output filtering, local gain (Cursor-friendly)

Inferred · not functionally tested

Open SourceMITWebCLI
pyrtkai preview
Visit github.com

Overview

5 features

Purpose: Reducing security risks and unpredictable behavior when running AI agents via the command line.

Inferred · not functionally tested

Audience: AI developers

Inferred · not functionally tested

Functions: Unknown

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.

In the AI & LLM security space, pyrtkai takes a focused approach. Inferred · not functionally tested: It focuses on reducing security risks and unpredictable behavior when running AI agents via the command line. Inferred · not functionally tested: pyrtkai is an open-source project aimed at AI developers. Basis unknown · not verified: pyrtkai is open source under the MIT license. Basis unknown · not verified: It runs on the web and the command line.

Behind pyrtkai is irmedvedeva, and it first shipped in 2026. The project is developed in the open on GitHub with 30 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are no-shell proxy, fail-closed policy, and deterministic output filtering.

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

Tasks: Inferred · not functionally tested

  • No-shell proxy
  • Fail-closed policy
  • Deterministic output filtering
  • Local execution
  • Security hooks

Topics: Inferred · not functionally tested

Tags
cli-securityagent-sandboxoutput-filtering
AI capabilities
Text
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
BrowserCLI

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about pyrtkai

What is pyrtkai?
Inferred · not functionally tested: Pyrtkai focuses on reducing security risks and unpredictable behavior when running AI agents via the command line. It is catalogued under AI & LLM security on PulseGate.
Who is pyrtkai for?
Inferred · not functionally tested: pyrtkai is an open-source project built for AI developers.
Does pyrtkai have a free plan?
Basis unknown · not verified: Yes — pyrtkai is open source under the MIT license and free to use.
What platforms does pyrtkai run on?
Basis unknown · not verified: pyrtkai runs on the web and the command line.
Is pyrtkai still active?
PulseGate's liveness check found it on 9 Oct 2026. Its GitHub repository shows 30 commits in the last 90 days.
What are alternatives to pyrtkai?
Similar projects tracked by PulseGate include pfy, psi-agent, and playagent.pfypsi-agentplayagent
Who makes pyrtkai?
pyrtkai is developed by irmedvedeva.
When did pyrtkai launch?
pyrtkai first shipped in 2026.

Similar projects

Closest matches by what these projects do