Skip to content
Back to the index

agenttakt

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 4 Aug 2026. How this is checked

AgentTakt is a terminal-based (TUI) tool that lets users review, edit, and approve execution plans from AI agents using a node editor interface. It implements the Model Context Protocol (MCP) and is designed to add a human-in-the-loop safeguard for autonomous AI agents. The project is open-source under the MIT license and supports both English and Japanese interfaces.

Inferred · not functionally tested

Open SourceMITCLI
Visit PyPI

Overview

4 features

Purpose: Safely reviewing and approving potentially risky AI agent execution plans before they run.

Inferred · not functionally tested

Audience: developers

Inferred · not functionally tested

Functions: agents, collaboration

Inferred · not functionally tested

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

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

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, agenttakt takes a focused approach. Inferred · not functionally tested: Safely reviewing and approving potentially risky AI agent execution plans before they run. Inferred · not functionally tested: agenttakt is an open-source project aimed at developers. Basis unknown · not verified: agenttakt is open source under the MIT license. Basis unknown · not verified: agenttakt is available on the command line.

It is developed by ryoohshima, and it first shipped in 2026. The project is developed in the open on GitHub with 3 commits in the last 90 days. Inferred · not functionally tested: Among its 4 catalogued features are Plan Review, Node Editor, and Approval Workflow. Basis unknown · not verified: Catalogued interfaces include an MCP server.

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

Tasks: Inferred · not functionally tested

  • Plan Review
  • Node Editor
  • Approval Workflow
  • Terminal UI

Topics: Inferred · not functionally tested

Tags
agent-approvalmcp-tuiplan-editorai-agent-safetyterminal-ui
AI capabilities
Text

JSON profile · Text profile · Access guide

Built with & integrations

Connectors
MCP
Runs on
CLI

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHubActive maintenance

Indexing history

2

What PulseGate has recorded for this listing

  1. Indexed21 Sep · 06:38 UTC
    agenttakt seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  2. Indexed4 Aug · 07:11 UTC
    agenttakt seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about agenttakt

What is agenttakt?
Inferred · not functionally tested: Safely reviewing and approving potentially risky AI agent execution plans before they run. It is catalogued under AI security & guardrails on PulseGate.
Who is agenttakt for?
Inferred · not functionally tested: agenttakt is an open-source project built for developers.
Does agenttakt have a free plan?
Basis unknown · not verified: Yes — agenttakt is open source under the MIT license and free to use.
What platforms does agenttakt run on?
Basis unknown · not verified: agenttakt runs on the command line.
Is agenttakt still active?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 3 commits in the last 90 days.
What projects are similar to agenttakt?
Similar projects tracked by PulseGate include agent-ps, agent-tco, and agt-agent.agent-psagent-tcoagt-agent
Who makes agenttakt?
agenttakt is developed by ryoohshima.
How long has agenttakt been around?
agenttakt first shipped in 2026.

Similar projects

Closest matches by what these projects do