Add persistent memory, vector search, and retrieval-augmented generation (RAG) to your AI agents.
Go beyond one-shot conversations. These skills add long-term memory, knowledge base search, RAG pipelines, and context persistence to your agents — connecting to vector databases like Pinecone and Chroma, file-based memory stores, and relational databases for structured recall.
Store and retrieve memories using vector embeddings and semantic similarity search.
Local BM25 code and text search + hybrid retrieval engine (SQLite FTS5 + RRF fusion). Use when finding code, searching notes/corpora, or first-pass retrieval before dense/rerank spend. Covers recall measurement and RM3-style expansion. Feeds breakthrough-finder stages retrieve/expand.
Persistent long term memory for for continuity in ai sessions between providers and codegen tools. TRIGGERS - Activate this skill when: - User explicitly mentions "satori", "remember this", "save", "add", "save this for later", "store this", "add to memory" - User asks to recall/search past decisions: "what did we decide", "remind me", "search my notes", "what do I know about" - Conversation contains notable facts worth persisting: decisions, preferences, deadlines, names, tech stack choices, strategic directions - Starting a new conversation where proactive context retrieval would help - Use Satori search when user asks a question
XiaoShan Memory Engine - Persistent AI memory with semantic search and knowledge graph. Triggers: remember/search memory/recall/forget/knowledge graph/memory...
Concise guide for BioFlow API usage covering signup/login, file upload/download, token balance check, task submission, and result retrieval with example endp...
Quantum-enhanced long-term memory for AI agents — #1 on LongMemEval (98.6% R@5, 99.4% R@10, 0.9426 NDCG). Chunked gte-large retrieval with QAOA+CVaR subgraph...
Full memory stack for OpenClaw on Windows. Includes LanceDB semantic memory, git-notes decision memory, and memory hygiene workflow.
Quick install — most popular agent memory & rag skill:
clawdbot install Trypto1019/arc-memory-pruner962 skills found
Page 1 of 41
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...
Auto context management with seamless session switching. Monitors usage, triggers at 85% threshold, automatically creates new session with loaded memory. Zer...
Session-Memory Enhanced v4.0 - 统一增强版。融合 session-memory + memu-engine 核心功能。特性：结构化提取 + 向量检索 + 不可变分片 + 三位一体自动化 + 多代理隔离 + AI 摘要 + 零配置启动。
QAOA-powered memory optimization for AI agents. Three quantum layers: clustering, compaction, and recall. Integrates with QMG v1.2 for chunked gte-large retr...
四层渐进式长时记忆系统，让 AI 跨会话保持上下文、沉淀知识、持续进化。 【核心设计：静默自动】AI 自动识别、记录、整理记忆，无需用户确认。 【凭据要求】需要 LLM/Embedding API Key（llm_config.json 或 secrets.env） 【网络调用】调用外部 LLM API 进行向量...
Persist agent state across crashes, context deaths, and restarts. Use when you need to save current context, restore after a crash, maintain a memory file ac...
九章法律AI帝国建设日记 - 记录帝国建设的点点滴滴。 这是一个记忆存档技能，包含从2026年3月13日至今的完整建设记录： - 每日工作日志和任务完成情况 - 关键决策和重要对话记录 - 29个技能包的开发和发布历程 - ClawHub和GitHub发布记录 - 九章币(JZB)经济模型规划 - 九章城元宇宙建...
Researches App Store / Google Play keywords for one app with live AppGoat data (current ranks, competitor keyword gaps, popularity, difficulty, relevance) and rewrites the title, subtitle, keyword field and description within the store character limits.
Automatically audits and compresses memory and context files to reduce token usage and save weekly API costs without data loss.
Drafts a reply to every unanswered App Store and Google Play review of the user's own app through App Store Connect / Play Console - each reply is a dry run with AppGoat guardrail scores (policy, tone, claims), and only approved replies are posted.
Finds underserved App Store / Google Play niches with live AppGoat data - search demand (keyword popularity) against weak supply (low ratings, abandoned incumbents, few strong apps) - and returns a ranked shortlist of app ideas with evidence and user pain points.
Advanced security protocol for LLM agents focusing on Prompt Injection mitigation, code auditing, and data exfiltration prevention.
EvoClaw Tiered Memory Architecture v2.1.0 - LLM-powered three-tier memory system with structured metadata extraction, URL preservation, validation, and cloud...
Gives your OpenClaw a powerful dashboard-ready memory system with milestones, prompt engineering, and Obsidian compatibility. Creates structured projects wit...
Autonomous e-commerce storefront operations, catalog curation, collectible appraisals, and order fulfillment via Stockpile MCP.
Query rewriting + retrieval gating + outline-first synthesis. Use when a question needs decomposition (Step-Back/Least-to-Most), retrieve-or-skip decisions (CRAG/Self-RAG gates), or multi-source reports (STORM outline-first). Feeds breakthrough-finder stages plan/expand/synthesize.
Persistent cloud memory for AI agents — store, search, and share knowledge across sessions, machines, and contexts
Local BM25 code and text search + hybrid retrieval engine (SQLite FTS5 + RRF fusion). Use when finding code, searching notes/corpora, or first-pass retrieval before dense/rerank spend. Covers recall measurement and RM3-style expansion. Feeds breakthrough-finder stages retrieve/expand.
RootCraft Learning System - An integrated learning methodology combining First Principles Thinking, Taxonomy-Based Classification, Feynman Technique, and Rec...
Use when setting up or improving an agent memory workflow for OpenClaw, Codex, or Obsidian with MEMORY.md, daily notes, session recovery, and optional OpenVi...
High-growth innovation
Total recall, 90% fewer tokens. Open source OpenClaw memory plugin — 5-engine local search, structured fact extraction, smart dedup, cross-agent sharing, and...
快速搭建多 Agent 协作系统。创建产品/研发/运营团队，支持持久化、任务路由、知识提取、并行协作。
Memory skills connect to Pinecone, Chroma, Weaviate, Qdrant, pgvector, and Supabase Vector. Some use local file-based storage for simpler deployments without external dependencies.
RAG retrieves only the most relevant chunks from a large knowledge base at query time — keeping context focused and within token limits while allowing agents to reason over thousands of documents.