tiered-recall-memory分层回忆系统 - 解决上下文长度限制,保持项目延续性。每次新session自动加载核心记忆+最近日志+活跃项目,支持手动深度回忆。索引含10字内摘要,方便区分同名条目。
Install via ClawdBot CLI:
clawdbot install davidme6/tiered-recall-memoryGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.com/skill/tiered-recallAudited Apr 17, 2026 · audit v1.0
Generated May 9, 2026
A freelance web developer works on multiple client projects spanning weeks. Using Tiered Recall, each new session automatically loads core memories, recent logs, and active project files, ensuring seamless continuation without manual context restoration.
An indie game developer manages a complex game project over many days. The skill auto-loads the latest progress, bug fixes, and feature discussions, allowing immediate focus on current tasks like version iteration and testing.
A content creator producing a series of educational guides uses the system to recall previous chapter details, editorial decisions, and asset status across sessions, maintaining consistency and efficiency.
A small R&D team experimenting with multiple product ideas uses Tiered Recall to keep track of parallel experiments, hypotheses, and results from previous sessions, enabling informed decisions without revisiting the entire history.
An individual using AI as a personal assistant for daily tasks, learning, and project management benefits from the skill's automatic loading of personal preferences, ongoing tasks, and recent notes, minimizing repetitive introductions.
Offer Tiered Recall as part of a premium AI assistant subscription for professionals who need continuous context across sessions. Revenue comes from monthly or annual subscriptions.
License the skill to enterprises for integration with internal AI tools, supporting knowledge continuity for remote teams. Revenue from per-seat licensing or flat enterprise fees.
Provide basic automatic recall (limited layers/tokens) for free, and charge for advanced features like deeper recall budgets, custom indexes, and priority indexing. Revenue from premium tier upgrades.
💬 Integration Tip
Integrate Tiered Recall by placing all memory files (MEMORY.md, daily logs, index) in a structured workspace within the AI's accessible directory. Configure the config.json to match typical token budgets and ensure the auto-load scripts run at session start.
Scored May 9, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Automatically prune and compact agent memory files to prevent unbounded growth. Circular buffer for logs, importance-based retention for state, and configura...
Founder onboarding interview that captures company context across 7 dimensions. Invoke with /cs:setup for initial interview or /cs:update for quarterly refre...
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vib...
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder rera...