Skip to content
Back to the index

mini-harness

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 1 Jul 2026. How this is checked

mini-harness is an open-source minimal agent harness core for AI developers. It features a ReAct loop, tool registry, and permission model, enabling the creation and management of AI agents with integrated tools and controlled permissions.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

5 features

Purpose: Providing a minimal framework for building and managing AI agents with tool integration and permission control.

Inferred · not functionally tested

Audience: AI developers building agent frameworks

Inferred · not functionally tested

Functions: agents

Inferred · not functionally tested

Interfaces: API: unknown · 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.

In the Frameworks & runtimes space, mini-harness takes a focused approach. Inferred · not functionally tested: It focuses on providing a minimal framework for building and managing AI agents with tool integration and permission control. Inferred · not functionally tested: It is built as an open-source project for AI developers building agent frameworks. Basis unknown · not verified: mini-harness is open source under the MIT license. Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

Behind mini-harness is JIANGXIADADAO, and it first shipped in 2026. Inferred · not functionally tested: Among its 5 catalogued features are reAct loop, tool registry, and permission model.

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

Tasks: Inferred · not functionally tested

  • ReAct loop
  • Tool registry
  • Permission model
  • Minimal core
  • Open source

Topics: Inferred · not functionally tested

Tags
agent-frameworkreact-looptool-registrypermission-modelopen-source
AI capabilities
Code
Weights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHub

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about mini-harness

What does mini-harness do?
Inferred · not functionally tested: Mini-harness focuses on providing a minimal framework for building and managing AI agents with tool integration and permission control. It is catalogued under Frameworks & runtimes on PulseGate.
Who should use mini-harness?
Inferred · not functionally tested: mini-harness is an open-source project built for AI developers building agent frameworks.
Is mini-harness free?
Basis unknown · not verified: Yes — mini-harness is open source under the MIT license and free to use.
What platforms does mini-harness run on?
Basis unknown · not verified: mini-harness runs on the command line. It can also be self-hosted.
Is mini-harness still active?
PulseGate's liveness check found it on 14 Sep 2026.
What are alternatives to mini-harness?
Similar projects tracked by PulseGate include minimal-harness, diy-harness, and subagent-harness-mcp.minimal-harnessdiy-harnesssubagent-harness-mcp
Who makes mini-harness?
mini-harness is developed by JIANGXIADADAO.
When did mini-harness launch?
mini-harness first shipped in 2026.

Similar projects

Closest matches by what these projects do