cortex
CortexPrism/cortex
CortexPrism is a self-hosted AI agent operating system providing persistent memory, multi-agent orchestration, sandboxed execution, and an embedded web interface built on Deno and TypeScript.
194 51Apache-2.0Updated 2026-06-25
77
GreatOverview
CortexPrism acts as a comprehensive autonomous agent runtime that converts standard LLMs into feature-complete digital agents. It organizes functionality into distinct core packages handling configuration, secure gatekeeping, AI orchestration, servers, infrastructure, and CLI tooling. Key capabilities include multi-user collaboration, encrypted credential vaults, modular pipeline stages, and decentralized agent swarm coordination.
Capabilities
- ▸Persistent episodic and semantic memory storage
- ▸Multi-agent coordination and swarm orchestration
- ▸Sandboxed code execution and virtual file system
- ▸Multi-layer security policy enforcement and vault storage
- ▸Multi-provider LLM routing and cascading strategy
- ▸Built-in web dashboard and REST API server
Best for
Running autonomous background AI agent workflows with persistent memory and tool use., Deploying a self-hosted multi-user AI assistant dashboard with role-based access control., Orchestrating distributed multi-agent swarms across multiple execution nodes., Executing sandboxed code snippets securely using policy enforcement and human-in-the-loop approvals.
Works with
Claude CodeCodexCursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
77Task 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%85 → +12.8
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%40 → +4.8
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%62 → +5.0
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 total77.0 / 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
Implements a three-layer security model (Parallax) consisting of regex policy validators, fast LLM supervisors, and explicit human approvals. Credentials are encrypted via AES-256-GCM using PBKDF2 key derivation.
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.