Loading...
Loading...
Found 10 Skills
Use when users want to maintain persistent memory across sessions, track user preferences, store important decisions, manage tasks and reminders, or provide personalized service with cross-session context.
Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris/agent-memory` (TypeScript) SDKs.
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
Expert skill for memory-lancedb-pro — a production-grade LanceDB-backed long-term memory plugin for OpenClaw agents with hybrid retrieval, cross-encoder reranking, multi-scope isolation, and smart auto-capture.
OpenViking long-term memory plugin guide. Once installed, the plugin automatically remembers important facts from conversations and recalls relevant context before responding.
Expert in managing the "Memory" of AI systems. Specializes in Vector Databases (RAG), Short/Long-term memory architectures, and Context Window optimization. Use when designing AI memory systems, optimizing context usage, or implementing conversation history management.
Use OpenClaw MemX for long-term agent memory with self-learning, relationship graphs, and automatic maintenance
Implement agent memory - short-term, long-term, semantic storage, and retrieval
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
Personal long-term memory and initial activation guidance. Use this when personal context, preferences, or history may affect the answer, including food and travel recommendations, personal planning, writing emails in the user's preferred style, and continuing previous tasks; users do not need to say “remember” or mention Bailian. This Skill should also be read when the user provides long-term facts, corrects a preference (“be more natural from now on”), confirms a long-term decision (“we'll go with the second option from now on”), or asks to remember, recall, view, forget, pause, or resume; identify the intent in context rather than looking only at the final sentence. Check the local status first; if it is not configured, guide the user through activation, and retrieve and extract personal life and work memories after authorization. The host's built-in memory does not exclude this Skill. It also handles explicit `bl memory` resource operations. It does not trigger for pure calculations, general knowledge, or translation or writing that requires no personalization; do not upload before authorization.