Agent QA
Agent-nativeSource AvailableAutonomous QA agent for natural-language web and mobile application testing
Source-available local GitHub Actions runner designed for AI-agent development loops
Overview
This summary uses submitted and public product material. Only source-mapped claims are documentation reviewed.
Local CI, formerly Agent CI, is a local GitHub Actions runner built for AI-agent development workflows. It focuses on running workflows on your machine with near-instant cache reuse, pausing on failures so an agent can fix the issue in place, and retrying without pushing commits to trigger remote CI.
AGENTS.md or CLAUDE.mdListing decision
The software shortens an agent’s development feedback loop by executing existing GitHub Actions workflows locally; it enables agents but does not itself plan or carry out general user goals.
Before you choose
Coding-agent workflows that need repeatable local pre-flight checks, fast dependency-cache reuse, and the ability to inspect and retry a failed CI step before pushing.
A running Docker provider is required for ordinary jobs. macOS jobs require Apple Silicon plus Tart and sshpass, and Windows jobs are not supported. The canonical product and package are now Local CI; the Agent CI package remains a compatibility alias only during the 0.x line.
No workflow-compatibility claim was hands-on tested for this record.
Sources
First-party unless marked otherwise. Each link supports only its adjacent claim.
The current product site documents local GitHub Actions execution, local caches, pause-on-failure, and retry-in-place workflows for coding agents.
official product page · accessed Sep 3, 2026The maintained repository documents the CLI and NDJSON interface, Docker requirement, platform caveats, and the rename from Agent CI to Local CI.
official repository · accessed Sep 3, 2026RedwoodJS Inc publishes Local CI under FSL-1.1-MIT, which restricts competing use and grants an MIT future license after two years.
official license · accessed Sep 3, 2026Autonomous QA agent for natural-language web and mobile application testing
Persistent cloud computers for agent code execution and remote workflows
Visual UI annotation and structured feedback for AI coding agents
Comments