Loading...
Loading...
Found 104 Skills
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"
Use when connecting to a self-hosted memory backend, searching, storing, or managing memories, importing connection tokens, or troubleshooting retrieval issues. Use this skill whenever the user mentions memory search, RAG retrieval, embedding, memory storage, multimodal document upload, knowledge queries, or wants to connect to a memory service, even if they do not explicitly say "transcendence-memory".
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading. A core context engineering skill — also activates when the user mentions "context engineering" or "context-engineering" in the context of extending context beyond the window via filesystem strategies.
Build hierarchical memory systems for AI agents using GAM (General Agentic Memory) with text, video, and long-horizon trajectory support
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
Migrate memory blocks from an existing agent to the current agent. Use when the user wants to copy or share memory from another agent, or during /init when setting up a new agent that should inherit memory from an existing one.
Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history.
Build structured hierarchical memory systems for LLM agents using GAM (General Agentic Memory) with support for text, video, and agent trajectories
ALWAYS ACTIVE — Persistent memory protocol. You MUST save decisions, conventions, bugs, and discoveries to engram proactively. Do NOT wait for the user to ask.
Expert in deploying and using Hermes HUD Web UI for monitoring AI agent memory, sessions, costs, and health
Cognitive memory management — encode, recall, forget, set reminders, and maintain long-term knowledge using personality-modulated memory.
Compile durable knowledge into interlinked-markdown stores the "karpathy method" way — atomic files, [[wiki-links]], a maintained index. Use after producing research, intel, a digest, a learned non-obvious fact, or finishing any knowledge-shaped task, BEFORE you close it. Also when asked to "save this", "write this to the wiki", "update the wiki/memory", "log this finding", "structure this knowledge", or "follow the karpathy method".