fleet

Name: fleet
Rating: 77 (1 reviews)
Author: brizzai

brizzai/fleet

Fleet is a terminal cockpit and CLI tool that orchestrates multiple Claude Code, Codex, and OpenCode sessions in parallel using git worktrees and tmux.

48 5Apache-2.0Updated 2026-08-10

Great

View on GitHub Open source file

Overview

Fleet provides a centralized interface for running, monitoring, and managing multiple coding agent sessions simultaneously. By leveraging native agent hooks and git worktrees, it enables developers to isolate independent tasks, track real-time agent status, fork conversations, and seamlessly jump between different active sessions without workflow collisions.

Capabilities

▸Run parallel AI coding agent sessions using Claude Code, Codex, and OpenCode
▸Isolate sessions within dedicated git worktrees
▸Real-time status tracking via agent hooks and pane heuristics
▸Message and direct running agent sessions via CLI or TUI
▸Fork existing agent sessions to experiment with alternative approaches
▸Suspend and resume idle sessions to manage system memory

Best for

Spawning a background agent session to tackle an independent bug fix or feature implementation in an isolated git worktree., Messaging running agent sessions with follow-up instructions or task adjustments., Monitoring the status of multiple concurrent coding agents and reviewing pull request states directly from the terminal.

Works with

Claude CodeCodexOpenCodeCursor

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%37 → +4.4

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%44 → +3.5

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total77.5 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

The skill enables automated execution of AI coding agents inside git worktrees and allows sending shell commands or prompts to active terminal sessions. Ensure proper review of tasks given to background agents to prevent unintended code modifications.