“Agent memory”

Use when about to create, save, or update a memory file in the persistent memory directory, including "remember this", "save a memory", or auto-memory writes…

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts.

Use when Comet must decide whether a bounded semantic review packet contains a personal memory worth creating, updating, forgetting, or skipping.

Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget) to…

Agentic memory system for writers - track characters, relationships, scenes, and themes

Creates a focused memory bank for the current project iteration using scope, git history, and tests.

Consolidate and clean up existing brain memory.

Manage project memory with MEMORY.md index + modular rule packs.

使用于 Comet 需要根据有界语义评审包判断是否值得保存个人记忆、候选、更新、遗忘或跳过时。

Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence.

Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget…

Store knowledge, code findings, conventions, or any text into Agent Replay's local memory.

Use when enabling, checking, or repairing local Holographic memory for selected existing Hermes Agent profiles or a verified repo Compose home; not for…

Extract durable learnings and preferences from the current conversation for memory capture.

Semantic recall, exact cross-session search, remembering, and normal continuity

Automated mnemon memory persistence workflow — recall on start, recall before each turn, auto-save after each response via delegated subagent.

Use when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role.

Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source.

Expert-level AgentScope developer skill for building production-ready LLM agents.

Gerencia memorias auto-aprendidas do projeto GSD.

Long-term memory.

Search past conversations for context, decisions, and patterns.

A file-based lesson memory that Claude Fable 5 / 5.1 reads and maintains across sessions.

Comprehensive interactive testing of all Memory MCP features