Mnemosyne
HomericIntelligence/Mnemosyne
Mnemosyne is a centralized skills and session-memory store designed to capture, organize, and share technical knowledge across development ecosystems.
14 4BSD-3-ClauseUpdated 2026-08-13
76
GreatOverview
Mnemosyne acts as the foundational knowledge repository for the HomericIntelligence agentic ecosystem. It uses structured markdown files with YAML frontmatter to record development learnings, debugging steps, experimental parameters, and failed attempts. Through integration commands like `/advise` and `/learn`, AI agents can query past insights before starting work or automatically document new findings in pull requests, preventing repeated mistakes.
Capabilities
- ▸Stores flat-file skills with YAML frontmatter and markdown sections
- ▸Integrates with search workflows to retrieve past context and avoid repeated mistakes
- ▸Automates pull request creation and git worktree isolation for new learnings via `/learn`
- ▸Supports modular supporting notes and historical version archives
- ▸Implements user prompt hooks to remind agents about saving session takeaways
Best for
Querying past debugging sessions and experimental parameters before starting new tasks via `/advise`., Automatically capturing session learnings, successes, and failures into standardized skill documents via `/learn`., Maintaining reusable, repository-agnostic development patterns and workflows.
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
76Task 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%46 → +5.5
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%34 → +2.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
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 total76.1 / 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 skill repository operates locally via git worktrees and manages markdown documentation files. Standard code execution security applies when running local test suites or validation scripts through uv.
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.