muxi
MCP Servermuxi-ai/muxi
Muxi is an open-source AI application server and infrastructure platform for deploying and managing production-ready agent formations. It offers built-in orchestration, declarative configurations, layered memory, RBAC, and multi-tenancy support.
194 14No licenseUpdated 2026-08-05
71
GoodOverview
Muxi acts as an infrastructure layer rather than a mere framework, providing a self-hosted server stack where AI agents are treated as native primitives. It streamlines the deployment, scaling, and operational management of complex agent formations through simple command-line tools, robust SDKs across twelve languages, and the Agent Formation Standard specification.
Capabilities
- ▸Declarative agent formations via the Agent Formation Standard
- ▸Layered and auditable memory systems with data provenance
- ▸Group-based role-based access control (RBAC)
- ▸Multi-tenant user isolation and credential management
- ▸Proactive agent behavior including heartbeats and notifications
- ▸Reasoning RAG with hierarchical document trees
- ▸Built-in production resilience with circuit breakers and retries
- ▸Extensive observability and lifecycle event tracing
Best for
Deploying scalable, production-ready multi-agent systems and applications, Managing secure, multi-tenant AI interactions with role-based access control, Integrating stateful agent formations with existing backend architectures using native SDKs, Implementing advanced RAG pipelines, reasoning workflows, and proactive agent behaviors
Works with
Claude CodeCodexCursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
71Task 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%44 → +5.3
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%80 → +12.0
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%59 → +4.7
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 total84.0 / 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
Muxi implements group-based RBAC, encrypted credentials, user-scoped memory isolation, and built-in PII redaction before log export.
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.