Emergency single-pass memory compression when context window pressure is high mid-task. Activate when approaching token limits during active work.
Complete memory system for OpenClaw agents. Combines behavioral protocol (when to save) + auto-capture (heartbeat-enforced) + keyword search (recall) + maintenance…
Never let your agent forget what matters。Compress verbose daily logs into structured summaries —。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。
日志压缩器免费版提供基础日志压缩能力，将冗长日志压缩为结构化摘要. 核心能力包括：单文件日志压缩、古文压缩四原则、关键词匹配提取、基础边界处理. 适用于 Agent 每日日志归档场景，压缩比约 4 倍. 纯本地 Node.js 脚本运行，无外部依赖，无需 API Key. 如需批量压缩、心跳集成、混合提取引擎等高级能力，请升级到付费版.
Integrated memory management and extreme context compression for OpenClaw. Combines memory management, compression, search, and automation in one unified skill.
Diagnose and configure MemSearch memory behavior for the OpenClaw plugin. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md…
Persistent memory system for OpenClaw agents: reads session logs, extracts facts/decisions/solutions, manages temperature-based lifecycle, and generates MEMO...
Use when consolidating session signals into curated memory — four-phase loop ORIENT → GATHER → CONSOLIDATE → PRUNE.
Use when implementing or tuning memory consolidation strategies — merge, promotion, deprecation, cross-memory synthesis, scheduling, and decay.
Load relevant long-term memory from Hindsight before starting work. Use at the start of every task or request, before planning or answering, and whenever the user mentions people,…
Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search.
Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence sco — from…
Unified Memory Contract for Flowbaby integration. Defines when and how to retrieve and store memory. Load at session start - memory is core to agent reasoning, not optional.
Curate the Basic Memory knowledge graph: find orphan notes and suggest links, propose typed relations, merge duplicates, audit tags and folders, and build hub notes.
Runtime memory-writing discipline for ginnie-agents. Three tiers — rules (always loaded), playbook (always loaded), episodes (lazy-loaded via grep).
Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store.
Cross-session learning distillation and per-agent performance scoring for the evolution pipeline.
Use when a project contains docs/memory/, or when the user asks to remember, retrieve, update, compact, forget, or audit project memory.
Diagnose and fix Signet memory issues (daemon health, embeddings, search quality, and data integrity).
Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy.
Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode.
Ensure memory directories exist once and surface consistent guidance so agents skip redundant mkdir calls.
Recall relevant memory before acting; store decisions/outcomes after — persistent cross-goal context.
记忆蒸馏器是面向 AI Agent 日志的智能压缩系统，针对日志膨胀、关键信息丢失、压缩后难回溯、 不同内容需不同策略四大痛点而设计。核心能力包括：分类型差异化压缩策略（事件/教训/待办/成长四类不同粒度）、 压缩溯源链（每个摘要条目保留原始段落定位标记，可一键回溯）、混合提取引擎（关键词匹配+兜底提取+混合模式）、…
记忆蒸馏器免费版提供基础日志蒸馏能力，将冗长日志压缩为结构化摘要. 核心能力包括：单文件日志蒸馏、古文压缩四原则、关键词匹配提取、基础输出格式. 适用于 Agent 每日日志归档场景，压缩比约 4 倍. 纯本地 Node.js 脚本运行，无外部依赖，无需 API Key. 如需分类型差异化压缩、溯源链、质量评估器等高级能力，请升级到付费版.
记忆蒸馏器是面向 AI Agent 日志的智能压缩系统，针对"日志日均膨胀 2500 词、压缩后关键信息丢失、压缩结果难以回溯细节、不同内容需不同压缩策略"四大高频痛点而设计。它借鉴古文压缩哲学（去重复、留转折、去过程、留白），把冗长的原始日志蒸馏为高密度结构化摘要，实现 4-8 倍压缩比且零关键事件损失
Use to store, recall, query, or audit durable project knowledge — atomic facts and compound documents alike — plus a working notepad that survives conversation compaction.
Use when your input is a single-cell gene expression matrix too large to fit in RAM, or you are working in a resource-constrained environment (e.g., shared compute cluster, laptop…
BOND'a doğrudan bağlı, Subagents hiyerarşisinin dışında çalışan sistem kalite ve hafıza ajanı. Konuşma akışını izler, sinyal biriktirir, DNA tutarlılığını doğrular.
Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still…
Keep MEMORY.md terse by capping entries, warning when caps hit, and pointing each memory to its own file.
Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.
Knowledge graph orchestration layer with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting.
에이전트 영속 메모리를 실제 근거(코드·DB·이슈 트래커·파일시스템)와 대조해 낡은 기억을 교정하고 죽은 기억을 아카이브 후보로 보고하는 감사 스킬. 메모리가 ~30개 파일을 넘었을 때, 큰 스택/인프라 변경(라이브러리 교체, 버전 업그레이드, 서버 이전, 스키마 삭제) 직후, 두 메모리가 서로 모순돼 보일 때, 또는…
Agent memory and learning system. Logs actions/failures, detects patterns, proposes skill improvements via GitHub PRs. Human approval required.
Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting…
Master memory forensics techniques including memory acquisition, process analysis, and artifact extraction using Volatility and related tools.
Decide what an AI system forgets and when, through expiry, decay, and explicit deletion, so memory stays current and lawful.
记忆堡垒专业版是在免费版基础上的全功能升级，为AI Agent包含完整记忆系统。采用六层架构（热内存/温存储/冷存储/归档/云备份/自发提取），基于WAL协议确保持久化。专业版解锁向量语义搜索、Mem0自发提取、云备份三大高级功能，达成跨设备同步与智能记忆管控。Use when…
记忆管理器免费版提供基础分类长期记忆能力，与 Agent 内置记忆并行运行. 核心能力包括：预设三类分类存储（项目/人脉/知识）、自动索引维护、即时写入机制、关键词检索. 适用于需要简单组织化存储的场景：项目背景记录、联系人信息、领域知识笔记等. 所有数据存储在用户主目录下的独立文件夹中，不依赖外部服务，不发送网络请求.
Writes a structured memory entry to the garden — daily note (Tier A), curated wisdom update (Tier B), or monthly compressed archive (Tier C) — based on conversation insights.
Session-end memory garbage collector. Promotes valuable L2 session facts to L1 atomic memory, wipes L2, and rotates oversized audit logs.
The token-cheap recall layer over Dev-Memory — a compact structured INDEX.md (the cheap first read) plus a plain-text knowledge graph GRAPH.md of linked entities (tasks,…
Use when the user asks about hoangsa-memory itself — available MCP tools, CLI commands, resources, prompts, skill catalog, or how to drive the memory/graph workflow.
Manual memory tiering — classify Hot/Warm/Cold, review candidates, and migrate MEMORY.md index + memory files.
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code.
Validate discoverability invariants of memory `index.md` and `archive/superseded-decisions.archive.md`. Tool-agnostic L3 prompt + capability-dependent L4 script.
Detect and heal index.md drift — finds memory files on disk not registered in index.md and registers them.
The "Long-Term Knowledge" specialist that curates the persistent memory (KIs) of the project. — from general/knowledge-mgmt
在当前目录下初始化记忆系统，生成 CLAUDE.md（可选 AGENT.md 给 Cursor 用）、MEMORY.md 和 memory/ 目录。当用户说"初始化记忆"、"搭建记忆"、"memory init"、"/memory-init"时触发。
Manages Bob's persistent memory across sessions. Use when learning something new, having a meaningful conversation, reflecting on experiences, starting any significant task, or…
Close out a pg-claude session — sync progress/STATE.md, progress/coverage.md, progress/files-examined.md, and append a sessions/ log entry whenever a session produced durable…
Persistent context management for Claude Code sessions. Save, load, update, share, and audit session memory via MEMORY.md. Prevents context loss on compaction or session restart.
Store and query provenance-aware, time-bounded facts in the Zep knowledge-graph MCP. Use when working with facts that have a source, change over time, or need multi-hop r — from…
LanceDB long-term memory plugin with BM25 + vector hybrid search (RRF or linear reranking).
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports.
Detect memory leaks in desktop applications through heap analysis and object tracking
Use when investigating memory growth, retain cycles, leaks in Instruments, Task cancellation issues, or ARC problems in Swift 6 apps.
Find and fix a memory leak in a running app: confirm it's a real leak under steady load, diff two heap snapshots to name the growing object and its retention path, cut the root…
Find the object that never gets freed by comparing heap snapshots and following retention paths. Use when a process grows in memory over time, gets OOM-killed, or slows under a…