Skip to content
Back to the index

agent-run-diff

github.comInfrastructure

PulseGate's liveness check found it on 13 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 26 Jun 2026. How this is checked

agent-run-diff is a command-line tool that compares baseline and current runs of AI agents, surfacing regressions, new errors, failed tool calls, and output drift. It helps developers monitor and debug agent performance over time. Ideal for AI and LLM developers focused on reliability.

Inferred · not functionally tested

Open SourceMITWebCLI
agent-run-diff preview
Visit github.com
1star
5features
2026since

Overview

5 features

Purpose: Detecting regressions and errors in agent runs by comparing baseline and current outputs.

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.

agent-run-diff is an Agent evaluation & testing project. Inferred · not functionally tested: It focuses on detecting regressions and errors in agent runs by comparing baseline and current outputs. Inferred · not functionally tested: agent-run-diff is an open-source project aimed at AI developers. Basis unknown · not verified: agent-run-diff is open source under the MIT license. Basis unknown · not verified: It runs on the web and the command line.

It is developed by Mukunda Katta, 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 5 catalogued features are regression detection, error analysis, and output drift detection.

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

Tasks: Inferred · not functionally tested

  • Regression detection
  • Error analysis
  • Output drift detection
  • Latency tracking
  • Cost analysis

Topics: Inferred · not functionally tested

Tags
agent-evaluationregression-testingllm-observabilitycli-tooltrace-analysis
AI capabilities
Structured

JSON profile · Text profile · Access guide

Built with & integrations

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 agent-run-diff

What is agent-run-diff?
Inferred · not functionally tested: Agent-run-diff focuses on detecting regressions and errors in agent runs by comparing baseline and current outputs. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use agent-run-diff?
Inferred · not functionally tested: agent-run-diff is an open-source project built for AI developers.
Does agent-run-diff have a free plan?
Basis unknown · not verified: Yes — agent-run-diff is open source under the MIT license and free to use.
What platforms does agent-run-diff run on?
Basis unknown · not verified: agent-run-diff runs on the web and the command line.
Is agent-run-diff still maintained?
PulseGate's liveness check found it on 13 Sep 2026. Its GitHub repository shows 3 commits in the last 90 days.
What are alternatives to agent-run-diff?
Similar projects tracked by PulseGate include Nori, agentdiff-cli, and agent-diff-guard.Noriagentdiff-cliagent-diff-guard
Who develops agent-run-diff?
agent-run-diff is developed by Mukunda Katta.
When did agent-run-diff launch?
agent-run-diff first shipped in 2026.

Similar projects

Closest matches by what these projects do