total-recall
gavdalf/total-recall
Total Recall is an autonomous memory management skill that automatically observes, compresses, and consolidates agent conversations into prioritized markdown notes. It uses a zero-database, multi-layered redundancy architecture designed to run efficiently on free-tier LLM models.
272 41MITUpdated 2026-04-01
78
GreatOverview
This skill acts as an autonomous background observer for AI agents, capturing and compressing session transcripts into markdown files without requiring manual saves or vector databases. It implements a robust five-layer architecture including periodic observation, reactive inotify watchers, session recovery, pre-compaction flushing, and a nightly 'Dream Cycle' for long-term memory consolidation, importance decay, and pattern promotion.
Capabilities
- ▸Autonomous conversation compression into prioritized observations
- ▸Dynamic memory reflection and consolidation when logs grow large
- ▸Session recovery and emergency flushing before context compaction
- ▸Linux reactive monitoring via inotify for high-activity logging
- ▸Nightly Dream Cycle for importance decay, chunking, and archival
Best for
Maintaining cross-session context and memory for AI coding agents without manual saving, Consolidating large conversation logs to reduce token usage while preserving critical knowledge, Recovering missed session context upon agent startup or reset, Running automated nightly memory maintenance and archival via a Dream Cycle
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
78Task 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%70 → +10.5
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%51 → +6.1
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%64 → +5.1
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 total78.3 / 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
Requires an API key for LLM calls and executes background shell scripts via cron and systemd services. Ensure workspace permissions and log outputs are appropriately restricted.
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.