“agent memory”

Persist and retrieve repository-specific knowledge using AGENTS.md files.

Use when implementing or managing persistent, hierarchical memory systems for AI agents.

Implement agent memory with episodic, semantic, and procedural memory stores

Design agent memory systems with short-term, long-term, episodic, and semantic memory and retrieval strategies

A hybrid memory system that provides persistent, searchable knowledge management for AI agents.

Use Cognition-spec compliant Git-backed persistent memory to recall, write, and maintain durable cross-session knowledge across Universal and Project scopes.

Persist durable agent metadata after self-review, user review, PR comments, or a correction.

Persistent memory and context management for agent sessions.

Persistent memory system for AI agents — remember facts, learn from experience, and track entities across sessions.

AI 代理的记忆管理工具 - 列表显示、搜索查找、摘要生成及记忆文件维护。包含 AI 驱动的摘要功能。

Capture profile deltas, reflections, commitments, artifacts, and community learning into private-safe memory records.

Use when user asks to remember/save/recall/organize or when durable conventions/invariants/preferences are discovered; store with citations or evidence and…

Reviews agent memory and state-store configuration for correctness.

Persistent memory system.

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Design and implement memory systems for AI agents — short-term working context, episodic memory in vector stores, entity extraction into knowledge graphs…

Read and update project agent memory in .agents/memory/.

TypeDB-backed ontological memory with schema-driven retrieval.

Design tenant-scoped memory, retrieval and retention for agents.

Cognition-spec compliant Git-backed persistent memory repo for Pi coding agent and OMP.

Use Nate Jones OB1 Agent Memory from OpenClaw with provenance, scope, review, and use-policy discipline.

Memory is the cornerstone of intelligent agents.

Use when a plan, prompt, or doc still names agent-shared-memory.

Use this skill when you need evidence-bounded memory write/read/update/delete, retention, contamination, isolation, provenance, and forgetting behavior…