Skip to content
Back to the index

replay-agent

PyPIInfrastructure

PulseGate's liveness check found it on 14 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 29 Jun 2026. How this is checked

replay-agent is an open-source CLI tool that allows developers to record and replay traces of LLM agent executions, enabling deterministic regression testing. It is framework-agnostic and integrates natively with pytest, making it ideal for AI developers and QA engineers.

Inferred · not functionally tested

Open SourceMITCLI
Visit PyPI

Overview

5 features

Purpose: Enabling deterministic regression testing for LLM agents by recording and replaying agent traces.

Inferred · not functionally tested

Audience: AI developers and QA engineers

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: cli

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

replay-agent sits in PulseGate's Agent evaluation & testing category. Inferred · not functionally tested: It focuses on enabling deterministic regression testing for LLM agents by recording and replaying agent traces. Inferred · not functionally tested: replay-agent is an open-source project aimed at AI developers and QA engineers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: replay-agent is available on the command line.

Behind replay-agent is Joshua Shley, and it first shipped in 2026. Inferred · not functionally tested: Key capabilities include trace recording, trace replay, and deterministic testing.

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

Tasks: Inferred · not functionally tested

  • Trace recording
  • Trace replay
  • Deterministic testing
  • Pytest integration
  • Framework agnostic

Topics: Inferred · not functionally tested

Tags
agent-testingtrace-replayregression-testingpytest-pluginllm-agents
AI capabilities
Code

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLI

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHub

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about replay-agent

What does replay-agent do?
Inferred · not functionally tested: Replay-agent focuses on enabling deterministic regression testing for LLM agents by recording and replaying agent traces. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use replay-agent?
Inferred · not functionally tested: replay-agent is an open-source project built for AI developers and QA engineers.
Is replay-agent free?
Basis unknown · not verified: Yes — replay-agent is open source under the MIT license and free to use.
What platforms does replay-agent run on?
Basis unknown · not verified: replay-agent runs on the command line.
Is replay-agent still active?
PulseGate's liveness check found it on 14 Oct 2026.
What are alternatives to replay-agent?
Similar projects tracked by PulseGate include agent-replay-py, tool-call-replay, and replaylab.agent-replay-pytool-call-replayreplaylab
Who makes replay-agent?
replay-agent is developed by Joshua Shley.
How long has replay-agent been around?
replay-agent first shipped in 2026.

Similar projects

Closest matches by what these projects do

Submit to the index
Apps, agents and models — free, no signup.