Invoker
Neko-Catpital-Labs/Invoker
Invoker is a persisted multi-agent workflow orchestration platform that runs a DAG of tasks in isolated git worktrees. It coordinates AI agents, human review gates, and remote execution across a unified control plane.
Overview
Invoker provides a comprehensive workflow orchestration environment for software engineering tasks involving multiple AI agents. It maps tasks into a directed acyclic graph (DAG) executed inside isolated git worktrees, managing dependencies, merge gates, pull requests, and human intervention points. The platform bridges desktop clients, a command-line interface, and Slack channels, allowing developers to monitor execution, drive tasks with models like Claude and Codex, and manage cloud or remote SSH targets from a single pane of glass.
Capabilities
- ▸Multi-agent workflow orchestration via task DAGs
- ▸Execution isolation using git worktrees
- ▸Human-in-the-loop intervention and approval gates
- ▸Unified control plane spanning desktop, CLI, and Slack
- ▸Remote agent control over SSH and cloud targets
- ▸Automated failed-task recovery and PR maintenance workers
Best for
Orchestrating complex multi-step software development workflows using multiple AI agents, Running automated task execution within isolated git worktrees with strict merge gates, Managing and reviewing stacked code changes, pull requests, and conflict resolutions, Controlling remote agents and cloud machines via desktop, CLI, or Slack interfaces
Works with
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
実装・指示の品質。 — AIによるSKILL.md/README解析
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
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
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
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
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
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
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
Invoker executes AI agents and automates git operations, modifying code repositories and interacting with remote systems via SSH and APIs. Users should carefully review agent plans and verify permissions on remote targets.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.