iai-personal-memory-engine
MCP ServerCodeAbra/iai-personal-memory-engine
iai-personal-memory-engine (iai-pme) is a local, ambient personal memory engine for AI coding assistants that captures interactions verbatim and serves context via the Model Context Protocol (MCP).
499 59MITUpdated 2026-08-12
85
GreatOverview
Designed as a privacy-first, local-only memory solution, iai-pme runs entirely on your machine without requiring external cloud accounts, telemetry, or API keys. It captures sessions word-for-word, organizes them into a hyperdimensional memory substrate with a custom storage engine, and injects relevant memory packs at session starts to reduce redundant searches and save considerable tokens.
Capabilities
- ▸Verbatim session capture and transcription storage
- ▸Local embedding generation and community-detection algorithms
- ▸Model Context Protocol (MCP) server compatibility
- ▸Token usage and savings dashboard tracking
- ▸Encrypted local storage via AES-256-GCM
Best for
Providing long-term memory across sessions for coding assistants like Claude Code, Cursor, and Codex CLI., Reducing token overhead by injecting concise, pre-computed memory packs instead of running expensive agent searches., Locally archiving historical interactions securely using AES-256-GCM encryption.
Works with
Claude CodeCodexCursor
Evoa Score breakdown= Σ (score × weight)
85Task 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%47 → +5.6
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%70 → +5.6
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 total84.6 / 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 operates locally with no telemetry and encrypts data at rest using AES-256-GCM.
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.