#
ENJA

AgentRecall-X

MCP Server

Goldentrii/AgentRecall-X

AgentRecall-X is a persistent memory and corrections ledger for coding agents that tracks session context and measures whether mistakes recur.

364 57MITUpdated 2026-08-04

Overview

AgentRecall-X provides automated memory management across sessions for AI coding assistants using Model Context Protocol (MCP), a CLI, and SDKs. It records session states, tracks user corrections to prevent recurring errors, and securely stores project history locally without requiring cloud infrastructure.

Capabilities

  • Automatic session lifecycle hook management (start and end)
  • Structured corrections ledger with evidence and outcome tracking
  • Local vector and keyword search retrieval using RRF fusion
  • Risk analysis and pre-action safety check verdicts

Best for

Maintaining persistent context across multiple AI coding sessions, Tracking and learning from user corrections to prevent repeating past mistakes, Pre-checking risky actions like deployment or deletion against past safety rules

Works with

Claude CodeCodexCursor
Evoa Score breakdown= Σ (score × weight)
80
Task usefulness20%77 → +15.4

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%31 → +3.7

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%100 → +15.0

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%67 → +5.4

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%75 → +3.8

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 total80.2 / 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

Operates entirely locally by default with zero cloud telemetry, ensuring project knowledge and source context remain private on the user's filesystem.

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.