ryanstephen/lil-agents

LilAgents is a macOS application that serves as a unified interface for managing multiple AI coding agents, including Gemini, OpenCode, and OpenClaw. It centralizes session management through a standardized protocol and provides a menu bar interface for selecting different agent providers. The system also includes logic to intelligently manage character visibility based on the user's screen layout and dock configuration.

LilAgents now supports a wider range of AI providers, adding native integration for Gemini, OpenCode, and OpenClaw alongside the existing Claude, Codex, and Copilot CLIs. The app introduces a unified \AgentSession\ protocol and a centralized \AgentProvider\ enum to manage these diverse backends, allowing users to select their preferred agent via a new menu bar submenu. Additionally, the application now includes a \DockVisibility\ module to intelligently handle character visibility based on screen layouts and dock states, and updates the Sparkle auto-update feed to point to the official repository.

LilAgents · high confidence

The application now supports additional AI agent providers, with new session implementations added for Codex, Copilot, Gemini, OpenCode, and OpenClaw, alongside core session and shell environment management. The project has been rebranded from 'DockWalker' to 'LilAgents', updating the app bundle name to 'lil agents' and the Xcode project target accordingly. Additionally, the build configuration was upgraded to Xcode 15.2 (LastUpgradeCheck 2620) with stricter compiler warnings enabled.

lil-agents.xcodeproj · high confidence

Added a new test suite (DockVisibilityTests) that verifies the DockVisibility.shouldShowCharacters function across various screen configurations, including bottom, left, and right dock positions, fullscreen spaces, and auto-hide states on main and non-main screens.

Tests · high confidence

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

• CAI 50 → 48 (-2.1)
• Rubric changed (rubric-2026.09.11 → rubric-2026.09.18) — scores are not directly comparable.

• Code Health 85 → 87 (+1.5)
• Architecture 100 → 100 (+0.0)
• Maturity 47 → 47 (+0.1)
• Readiness 26 → 23 (-2.5)
• Security 100 → 100 (+0.0)

• Dependency hygiene PARTLY measured — SwiftPM pinning read, dependency currency NOT established
• Documentation: no licence statement (README.md)
• Hotspot: LilAgents/CodexSession.swift (LilAgents/CodexSession.swift)
• Hotspot: LilAgents/OpenClawSession.swift (LilAgents/OpenClawSession.swift)
• Hotspot: LilAgents/TerminalView.swift (LilAgents/TerminalView.swift)
• Off-boarding risk: anonymized user #1

• Documentation: no installation or build instructions (README.md)
• Documentation: no usage examples (README.md)
• Off-boarding risk: anonymized user #1
• Outdated: sparkle

Written by watchdog.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

ryanstephen/lil-agents was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.