Retrieve persistent conversation memory via grep-style search from MEMORY.md and HISTORY.md.
npx skills add https://github.com/zeminroot/cheerclaw --skill memory-zeminroot
Please help me install this Agent Skill. Skill: memory Source: https://github.com/zeminroot/cheerclaw/tree/main/cheerclaw/skills/memory Command: npx skills add https://github.com/zeminroot/cheerclaw --skill memory-zeminroot
双层记忆系统，基于 grep 检索召回记忆信息。它提供跨会话的持久记忆能力，帮助保持上下文、偏好与关键事实在长期对话中的可用性。
Ask the agent to retrieve memory items related to a topic from MEMORY.md and HISTORY.md using grep-style search.
High-intent search queries and answers about installing and using this skill.
Persistent context across agent conversations is maintained using a two-layer memory system that stores original logs in origin_qas.jsonl, event summaries in HISTORY.md, and key facts in MEMORY.md for continuous recall.
Historical agent memory is searchable via grep-style retrieval to locate relevant entries in MEMORY.md and HISTORY.md, loading only matched items into the context for precise filtering and validation.
Managing user preferences in long-running support tasks is best handled by incrementally updating a persistent MEMORY.md file, ensuring core preference facts remain available across sessions.
This cross-session memory approach stores original conversation logs in the origin_qas.jsonl file, separating raw data from summarized events in HISTORY.md and long-term facts in MEMORY.md.
A two-layer memory model for agent context is needed during onboarding and long-running support tasks where preserving historical logs and summarizing incremental events ensures continuous knowledge accumulation.
Loading full conversation history into the agent context risks exceeding token limits, so controlled loading via grep-style search retrieves only relevant memory items to maintain robust validation.
EthanAlgoXRetrieve long-term facts and event logs via grep-based searches.
designnotdrumStore structured memories with facts, reasons, sentiment, and implications.
AcosmiSearch long-term memory by keyword with semantic retrieval and relevance scores.
mwathibenDesign hybrid retrieval fusing vector similarity with keyword matching.
