cortex-engine

Name: cortex-engine
Rating: 80 (1 reviews)
Author: Fozikio

MCP Server

Fozikio/cortex-engine

Cortex Engine provides persistent cognitive memory for AI agents, enabling knowledge retention across sessions through graph-based storage, contradiction detection, and spaced repetition.

49 6MITUpdated 2026-08-04

Great

View on GitHub Open source file

Overview

This tool supplies AI agents with a comprehensive, neuroscience-inspired memory layer built on top of Model Context Protocol (MCP) servers. It utilizes graph architectures, spreading activation, contradiction resolution via NLI, and sleep-like consolidation phases (dreaming) to allow agents to accumulate expertise, maintain evolving beliefs, and preserve context across multiple sessions.

Capabilities

▸Semantic memory querying and observation recording
▸Contradiction and tension detection using NLI models
▸Spaced repetition scheduling via FSRS and biological-inspired sleep consolidation (dreaming)
▸Graph neighborhood exploration and belief tracking
▸Multi-session operations logging and persistent thread management

Best for

Retaining project decisions, coding patterns, and architectural context across separate coding sessions, Conducting memory-grounded code reviews by checking new implementations against historical facts, Managing evolving project journals, multi-session exploration threads, and long-term agent goals

Works with

Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%88 → +17.6

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%41 → +4.9

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%45 → +3.6

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 total80.1 / 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 engine implements timing-safe authentication for REST endpoints, validates plugin import paths, and restricts destructive tools from generic REST access.