Back to Details

memory-reviewer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Memory Reviewer

Memory Reviewer

Audits memory quality for the active project. Finds duplicates, contradictions, and low-confidence entries.
审核当前项目的记忆质量，查找重复项、矛盾内容和低置信度条目。

When to use

使用场景

  • User asks "check my memories", "memory quality", "any duplicates?"
  • User runs 
    /mem0:memory-reviewer
    directly
  • After a session with 5+ memory writes (suggest proactively)
  • After 
    /mem0:health --deep
    identifies issues
  • 用户询问“检查我的记忆”“记忆质量”“有没有重复项？”
  • 用户直接运行 
    /mem0:memory-reviewer
  • 在完成包含5次以上记忆写入的会话后（建议主动触发）
  • 在 
    /mem0:health --deep
    识别出问题后

Steps

步骤

  1. Fetch all memories for active project via 
    get_memories
    with 
    filters={"AND": [{"user_id": "<active_user_id>"}, {"app_id": "<active_project_id>"}]}
    , 
    page_size=200
    . Paginate if needed — cap at 200 memories.
  2. Group by 
    metadata.type
    . Common types: 
    decision
    , 
    convention
    , 
    anti_pattern
    , 
    task_learning
    , 
    project_profile
    , 
    user_preference
    , 
    session_state
    .
  3. Scan each group for issues:
    IssueDetection method
    Near-duplicates>60% noun overlap within same type. Compare memory text after stripping stop words.
    ContradictionsOpposing facts about same topic (e.g., "use PostgreSQL" vs "use MySQL" for same component)
    Low-confidence
    metadata.confidence < 0.3
    Missing typeNo 
    metadata.type
    set
    Stale
    created_at
    older than 180 days with no updates
  4. Output compact summary:
memory-reviewer: project=<id> total=<N>
  duplicates:      <N> found
  contradictions:  <N> found
  low_confidence:  <N> found
  untagged:        <N> found
  stale:           <N> found
  1. If issues found, list them with memory IDs:
Issues:
  [duplicate] "<memory_a>" ≈ "<memory_b>" [mem0:<id_a>, mem0:<id_b>]
  [contradiction] "<memory_x>" vs "<memory_y>" [mem0:<id_x>, mem0:<id_y>]
  [low_conf] "<memory_z>" (confidence: 0.1) [mem0:<id_z>]
  1. Suggest action: "Run 
    /mem0:dream
    to consolidate duplicates and resolve contradictions."
  1. 获取所有记忆：通过 
    get_memories
    接口获取当前项目的所有记忆，参数为 
    filters={"AND": [{"user_id": "<active_user_id>"}, {"app_id": "<active_project_id>"}]}
    ，
    page_size=200
    。如有需要可分页扫描，但最多处理200条记忆。
  2. 按 
    metadata.type
    分组    。常见类型包括：
    decision
    、
    convention
    、
    anti_pattern
    、
    task_learning
    、
    project_profile
    、
    user_preference
    、
    session_state
    。
  3. 扫描每组内容以查找问题：
    问题类型检测方法
    近似重复项同一类型内名词重叠度超过60%。去除停用词后对比记忆文本。
    矛盾内容同一主题存在相反事实（例如，针对同一组件，“使用PostgreSQL”与“使用MySQL”）
    低置信度
    metadata.confidence < 0.3
    缺失类型标签未设置 
    metadata.type
    过期内容
    created_at
    超过180天且未更新
  4. 输出简洁摘要：
memory-reviewer: project=<id> total=<N>
  duplicates:      <N> found
  contradictions:  <N> found
  low_confidence:  <N> found
  untagged:        <N> found
  stale:           <N> found
  1. 若发现问题，列出问题及记忆ID：
Issues:
  [duplicate] "<memory_a>" ≈ "<memory_b>" [mem0:<id_a>, mem0:<id_b>]
  [contradiction] "<memory_x>" vs "<memory_y>" [mem0:<id_x>, mem0:<id_y>]
  [low_conf] "<memory_z>" (confidence: 0.1) [mem0:<id_z>]
  1. 建议操作：“运行 
    /mem0:dream
    来整合重复项并解决矛盾内容。”

Constraints

约束条件

  • Read-only — never modify or delete memories (that's 
    /mem0:dream
    's job)
  • Max 200 memories per scan
  • Report findings, let user decide on action
  • 只读操作——绝不修改或删除记忆（这是 
    /mem0:dream
    的职责）
  • 每次扫描最多处理200条记忆
  • 仅报告发现的问题，由用户决定后续操作