Skip to content
Back to the index

agentgrade

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

agentgrade is an open-source testing framework for multi-agent AI systems. It provides regression tests, credit assignment, and prompt patching, enabling developers and researchers to evaluate and improve agent workflows efficiently.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

5 features

Purpose: Testing and evaluating multi-agent AI workflows with automated regression and prompt patching.

Inferred · not functionally tested

Audience: AI developers and researchers

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 Agent evaluation & testing space, agentgrade takes a focused approach. Inferred · not functionally tested: It focuses on testing and evaluating multi-agent AI workflows with automated regression and prompt patching. Inferred · not functionally tested: agentgrade is an open-source project aimed at AI developers and researchers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: agentgrade is available on the command line, and it can be self-hosted.

Behind agentgrade is Shengyong Niu, and it first shipped in 2026. Inferred · not functionally tested: Key capabilities include regression testing, prompt patching, and credit assignment.

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

Tasks: Inferred · not functionally tested

  • Regression testing
  • Prompt patching
  • Credit assignment
  • Multi-agent support
  • Pytest integration

Topics: Inferred · not functionally tested

Tags
multi-agent-testingai-evaluationpytest-plugin
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 agentgrade

What does agentgrade do?
Inferred · not functionally tested: Agentgrade focuses on testing and evaluating multi-agent AI workflows with automated regression and prompt patching. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use agentgrade?
Inferred · not functionally tested: agentgrade is an open-source project built for AI developers and researchers.
Is agentgrade free?
Basis unknown · not verified: Yes — agentgrade is open source under the MIT license and free to use.
What platforms does agentgrade run on?
Basis unknown · not verified: agentgrade runs on the command line. It can also be self-hosted.
Is agentgrade still active?
PulseGate's liveness check found it on 14 Sep 2026.
What are alternatives to agentgrade?
Similar projects tracked by PulseGate include AgentGrade, agent-exam, and agents-gl.AgentGradeagent-examagents-gl
Who develops agentgrade?
agentgrade is developed by Shengyong Niu.
How long has agentgrade been around?
agentgrade first shipped in 2026.

Similar projects

Closest matches by what these projects do