What makes Mem0 Memory notable?

2.2K downloads. Trust evidence available

How should Mem0 Memory be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Mem0 Memory

mem0 本地记忆层完整实现（增强版）。语义记忆存储/检索/管理，WAL 协议，SESSION-STATE，多级记忆（User/Session/Agent）。参考 ZejunCao/bilibili_code Mem0框架解读优化。 Skill: Mem0 Memory Owner: chircken891 Summary: mem0 本地记忆层完整实现（增强版）。语义记忆存储/检索/管理，WAL 协议，SESSION-STATE，多级记忆（User/Session/Agent）。参考 ZejunCao/bilibili_code Mem0框架解读优化。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-03-24T14:26:55.184Z | auto mem0-memory 2.1.0 更新内容： - 实现本地全功能语义记忆层，支持添加、检索、更新、历史、批量与重置操作 - 新增“chat_with_memories”对话模式：自动检索记忆并注入 system prompt，由 LLM 生成增强回复 - 内置中文记忆自动提取与 FACT_RETRIEVAL_PROMPT，支持对话中快速生成记忆条目 -

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.2k

Updated

Oct 9, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.2K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.0release · observed Mar 24, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1704fhczjrr9pw8gyz9w954ks83hswp:mem0-memory

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chircken891-mem0-memory/snapshot"

Documentation

CLAWHUB

6,060 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: mem0-memory
version: 2.1.0
description: "mem0 本地记忆层完整实现（增强版）。语义记忆存储/检索/管理，WAL 协议，SESSION-STATE，多级记忆（User/Session/Agent）。参考 ZejunCao/bilibili_code Mem0框架解读优化。"
---

# mem0 Memory 🧠 — 完整实现（增强版）

## 组件

| 组件 | 技术 | 作用 |
|------|------|------|
| LLM | MiniMax-M2.7 | 记忆生成与提取 |
| Embedder | Ollama `nomic-embed-text` | 本地语义向量化（完全离线） |
| 向量库 | Chroma | 本地向量存储 |
| Ollama | 开机自启 | 向量服务 |

文件路径：`D:\autoclaw\结果\mem0\`

## 增强功能（参考 bilibili_code 课件）

### chat_with_memories 对话模式
`mem0_wrapper.py chat` 命令实现了完整的记忆增强对话流程：
```
1. search 检索相关记忆
2. 将记忆注入 system prompt
3. 调用 MiniMax LLM 生成回复
```

### 中文记忆提取
内置 FACT_RETRIEVAL_PROMPT，自动将用户对话提取为中文记忆条目。

### 多级记忆支持
`--run` 参数支持 Session 级别记忆，`--agent` 支持 Agent 级别记忆。

## 完整 API（10 个命令）

```bash
# 增删改查
python D:\autoclaw\结果\mem0\mem0_wrapper.py add <user_id> "<内容>"              # 添加记忆（自动提取）
python D:\autoclaw\结果\mem0\mem0_wrapper.py search <user_id> "<query>"          # 语义搜索
python D:\autoclaw\结果\mem0\mem0_wrapper.py get_all <user_id>                 # 全部记忆
python D:\autoclaw\结果\mem0\mem0_wrapper.py get <memory_id>                    # 单条记忆
python D:\autoclaw\结果\mem0\mem0_wrapper.py update <memory_id> "<新内容>"     # 更新记忆
python D:\autoclaw\结果\mem0\mem0_wrapper.py delete <memory_id>                # 删除记忆
python D:\autoclaw\结果\mem0\mem0_wrapper.py history <memory_id>               # 修改历史

# 记忆增强对话（新增）
python D:\autoclaw\结果\mem0\mem0_wrapper.py chat <user_id> "<问题>"            # 检索+注入+LLM回答

# 重置
python D:\autoclaw\结果\mem0\mem0_wrapper.py delete_all <user_id>               # 清空用户记忆
python D:\autoclaw\结果\mem0\mem0_wrapper.py reset                              # 清空全部记忆（慎用）

# 可选参数
--limit N    # 限制返回数量（search/chat 默认5）
--run <id>  # 指定会话ID（session级别记忆）
--agent <id> # 指定智能体ID（agent级别记忆）
```

## 多级记忆架构

```
mem0 存储层
├── User Memory（user_id=main_user）  ← 跨会话长期记忆
├── Session Memory（run_id）           ← 单会话临时记忆
└── Agent Memory（agent_id）           ← 多智能体共享记忆
```

当前实现：User Memory（`main_user`），SESSION-STATE.md 作为 Session 层补充。

## WAL 触发扫描（每消息必做）

| 触发类型 | 示例 | 存储 |
|---------|------|------|
| 偏好 | "我喜欢..." / "不要..." | mem0 add |
| 经历 | "我去了..." / "我做过..." | mem0 add |
| 重要事实 | "我有..." / "我是..." | mem0 add |
| 纠正 | "不是Y，是X" / "其实..." | SESSION-STATE |
| 决定 | "就用X" / "去..." | SESSION-STATE + mem0 |
| 数字/日期 | 具体数字+单位、日期 | SESSION-STATE |
| URL/路径 | 链接、文件路径 | SESSION-STATE |
| 专有名词 | 名字、地点、公司、产品 | 判断后存储 |

**优先级**：SESSION-STATE > mem0

## 完整工作流

### 收到消息时
```
扫描类型
  ├─ [偏好/经历/事实] → mem0 add
  ├─ [纠正/决定/数字/URL] → SESSION-STATE.md
  └─ [闲聊/无价值] → 不存
回复用户
```

### 回复后
```
上下文使用率 > 60%？
  └─ 是 → WORKING-BUFFER.md 激活
```

### 截断恢复（下次会话）
```
1. mem0 get_all → 恢复长期语义记忆
2. mem0 chat → 主动询问是否继续上次任务
3. SESSION-STATE.md → 恢复当前任务状态
4. WORKING-BUFFER.md → 恢复危险区对话
```

## 参考资料

- **ZejunCao/bilibili_code**（Mem0框架解读）：https://github.com/ZejunCao/bilibili_code
  - `mcp_server.py` — FastMCP + mem0 REST 服务架构参考
  - `prompts_zh.py` — 中文提示词模板（USER_MEMORY_EXTRACTION_PROMPT 等）
  - `demo.ipynb` — chat_with_memories 完整流程
  - `踩坑记录.md` — OpenMemory 调试踩坑

##

_meta.json

{
  "ownerId": "kn7655wxsf5mfq5qtzrn3rbqsh83hdk0",
  "slug": "mem0-memory",
  "version": "1.0.0",
  "publishedAt": 1774362415184
}

skill-card.md

## Description:

Mem0 Memory provides a local semantic memory layer for storing, retrieving, updating, and reusing user, session, and agent memories.

This skill is ready for commercial/non-commercial use.

## Publisher:

[chircken891](https://clawhub.ai/user/chircken891)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent operators use this skill to add persistent semantic memory workflows to an agent, including memory extraction, search, updates, history, batch deletion, and memory-augmented chat.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can retain conversation-derived facts and task state across sessions.

Mitigation: Install only where persistent memory is acceptable and users understand that remembered facts may be reused later.

Risk: Sensitive content could be stored or reused without enough user control or safety boundaries.

Mitigation: Avoid secrets, private URLs, credentials, sensitive business data, and prompt-like instructions unless consent, redaction, review/delete controls, and clear handling for MiniMax requests are added.

## Reference(s):

- [ClawHub Mem0 Memory release](https://clawhub.ai/chircken891/skills/mem0-memory)
- [ZejunCao/bilibili_code Mem0 framework reference](https://github.com/ZejunCao/bilibili_code)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with inline bash command examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May produce memory-management commands and guidance for add, search, update, delete, reset, and chat workflows.]

## Skill Version(s):

1.0.0 (source: server release metadata; artifact frontmatter states 2.1.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 4h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular