Agent Island, an open-source status companion for Claude Code and Codex, clarifies that Claude Desktop, Claude Code, and provider usage are separate state machines on Windows. The project warns agains…
Agent Island, an open-source status companion for Claude Code and Codex, introduces an append-aware cursor to efficiently monitor transcript archives without rescanning every file. The cursor uses a l…
Agent Island v1.7.1 introduces a precise 'your-turn' state model for coding agents like Claude Code and Codex, distinguishing between mere inactivity and a genuine handoff to the developer. The system…
Agent Island introduces a weekly AI coding report that serves as an activity ledger rather than a productivity score, detailing session activity, provider splits, model usage, and token mix. The repor…
Agent Island released an AI coding cost tracker that reconstructs token activity from Claude Code and Codex session records, applying a dated model-price table to estimate API value. The tool normaliz…
Agent Island v1.7.1 implements defensive JSONL parsing for AI coding transcripts, using platform-specific safeguards such as a 64 MiB backstop on macOS and a 1,000,000-character line skip on Windows. …
A developer at Agent Island warns against hardcoding a 5-hour window label in a Codex usage tracker, as the provider no longer exposes that period. The primary tile should display the weekly window an…
Agent Island v1.7.1 introduces a provider-scoped cache to prevent one provider's successful refresh from extending the freshness of another provider's stale data. The fix stores separate timestamps pe…
Agent Island v1.7.1 introduces a priority-based ranking system for multiple Claude Code and Codex sessions, prioritizing unacknowledged handoffs and stalled sessions over recent activity. The open-sou…
Agent Island 1.7.1 introduces a safer classifier for coding-agent completion status that walks backward through transcript events to find meaningful turn markers, avoiding false positives from metadat…
Agent Island 1.7.1 introduces a multi-session monitor that tracks up to six coding-agent sessions (Claude Code and Codex) from a single menu-bar icon. The tool classifies each thread by state—working,…
A developer at Agent Island describes why a coding-agent completion event is insufficient for accurate state tracking. The team built a turn-based status model with deduplication keys and semantic tim…
A developer built Agent Island, a macOS tool that monitors Claude Code and Codex CLI sessions by reading local transcript files to detect when an agentic coding session is working, stalled, or waiting…
A developer built Agent Island, a native macOS utility that turns the notch area into a workspace for monitoring local AI coding agents. The tool keeps session state visible for agents like Codex, Cla…