ax
google/ax
AX (Agent Executor) is a distributed harness runtime by Google designed to dynamically provision isolated, resumable environments for autonomous and long-running AI agents.
Overview
AX provides a foundational runtime layer for managing state, ensuring reliability, and auditing execution for complex agentic workloads. It features a single-writer architecture, durable event logging, and native recovery protocols, aiming to ease the productionization of agents on platforms like Kubernetes and Agent Substrate.
Capabilities
- ▸Distributed runtime and isolation
- ▸Automatic recovery and execution resumption
- ▸Single-writer state management with durable event logging
- ▸Support for frontier harnesses (e.g., Antigravity)
- ▸Model configuration via Google AI Studio and Vertex AI
Best for
Orchestrating long-running, autonomous AI agents in distributed environments, Suspending and resuming agent execution states across interruptions or idle periods, Deploying multi-tenant agent harnesses with integrated MCP tools and skills
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
Requires API credentials for LLM providers such as Google AI Studio or Google Cloud Vertex AI. Operates as a distributed server managing isolated execution environments.
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.