← 返回 Skills 市场
cs995279497-byte

Chen Memory Setup

作者 cs995279497-byte · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
116
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install chen-memory-setup
功能描述
Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure m...
使用说明 (SKILL.md)

Memory Setup Skill

Transform your agent from goldfish to elephant. This skill helps configure persistent memory for Moltbot/Clawdbot.

Quick Setup

1. Enable Memory Search in Config

Add to ~/.clawdbot/clawdbot.json (or moltbot.json):

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  }
}

2. Create Memory Structure

In your workspace, create:

workspace/
├── MEMORY.md              # Long-term curated memory
└── memory/
    ├── logs/              # Daily logs (YYYY-MM-DD.md)
    ├── projects/          # Project-specific context
    ├── groups/            # Group chat context
    └── system/            # Preferences, setup notes

3. Initialize MEMORY.md

Create MEMORY.md in workspace root:

# MEMORY.md — Long-Term Memory

## About [User Name]
- Key facts, preferences, context

## Active Projects
- Project summaries and status

## Decisions & Lessons
- Important choices made
- Lessons learned

## Preferences
- Communication style
- Tools and workflows

Config Options Explained

Setting Purpose Recommended
enabled Turn on memory search true
provider Embedding provider "voyage"
sources What to index ["memory", "sessions"]
indexMode When to index "hot" (real-time)
minScore Relevance threshold 0.3 (lower = more results)
maxResults Max snippets returned 20

Provider Options

  • voyage — Voyage AI embeddings (recommended)
  • openai — OpenAI embeddings
  • local — Local embeddings (no API needed)

Source Options

  • memory — MEMORY.md + memory/*.md files
  • sessions — Past conversation transcripts
  • both — Full context (recommended)

Daily Log Format

Create memory/logs/YYYY-MM-DD.md daily:

# YYYY-MM-DD — Daily Log

## [Time] — [Event/Task]
- What happened
- Decisions made
- Follow-ups needed

## [Time] — [Another Event]
- Details

Agent Instructions (AGENTS.md)

Add to your AGENTS.md for agent behavior:

## Memory Recall
Before answering questions about prior work, decisions, dates, people, preferences, or todos:
1. Run memory_search with relevant query
2. Use memory_get to pull specific lines if needed
3. If low confidence after search, say you checked

Troubleshooting

Memory search not working?

  1. Check memorySearch.enabled: true in config
  2. Verify MEMORY.md exists in workspace root
  3. Restart gateway: clawdbot gateway restart

Results not relevant?

  • Lower minScore to 0.2 for more results
  • Increase maxResults to 30
  • Check that memory files have meaningful content

Provider errors?

  • Voyage: Set VOYAGE_API_KEY in environment
  • OpenAI: Set OPENAI_API_KEY in environment
  • Use local provider if no API keys available

Verification

Test memory is working:

User: "What do you remember about [past topic]?"
Agent: [Should search memory and return relevant context]

If agent has no memory, config isn't applied. Restart gateway.

Full Config Example

{
  "memorySearch": {
    "enabled": true,
    "provider": "voyage",
    "sources": ["memory", "sessions"],
    "indexMode": "hot",
    "minScore": 0.3,
    "maxResults": 20
  },
  "workspace": "/path/to/your/workspace"
}

Why This Matters

Without memory:

  • Agent forgets everything between sessions
  • Repeats questions, loses context
  • No continuity on projects

With memory:

  • Recalls past conversations
  • Knows your preferences
  • Tracks project history
  • Builds relationship over time

Goldfish → Elephant. 🐘

安全使用建议
This skill appears to do what it says (configure memory) but check a few things before proceeding: 1) Verify the publisher/owner — the registry ownerId and _meta.json ownerId differ, which could indicate a copy/paste or repackaging; confirm you trust the source. 2) Back up your existing ~/.clawdbot/clawdbot.json and workspace before making changes. 3) Be cautious about enabling 'sources: ["sessions"]' — that will index past conversation transcripts and can surface sensitive data to whichever embedding provider you choose. 4) Only provide VOYAGE_API_KEY or OPENAI_API_KEY to trusted providers and understand how those providers store/process embeddings. 5) If you allow the agent to act autonomously, be aware it could modify config and restart the gateway; if you want manual control, don't grant autonomous execution or run the suggested commands yourself. 6) If anything looks unfamiliar (owner mismatch, unexpected workspace paths, unfamiliar provider names), ask the publisher for clarification before installing.
功能分析
Type: OpenClaw Skill Name: chen-memory-setup Version: 1.0.0 The skill bundle is a documentation-only guide for configuring persistent memory (RAG) for the OpenClaw agent. It contains no executable code, scripts, or suspicious dependencies, focusing instead on providing configuration templates for 'clawdbot.json' and organizational structures for memory files like 'MEMORY.md'. The instructions provided for the agent are standard operational procedures for memory retrieval and do not exhibit signs of malicious prompt injection or data exfiltration.
能力评估
Purpose & Capability
The name/description align with the SKILL.md: it configures memorySearch, MEMORY.md, and memory/ logs — all expected. However, the documentation references setting VOYAGE_API_KEY and OPENAI_API_KEY although the skill's declared requirements list no environment variables; additionally the registry ownerId differs from the _meta.json ownerId, which suggests a packaging/metadata inconsistency that merits verification.
Instruction Scope
The instructions are narrowly scoped to editing ~/.clawdbot/clawdbot.json (or moltbot.json), creating workspace memory files, and restarting the gateway. Those actions are coherent with enabling memory. Important privacy/operational implications: it recommends indexing 'sessions' (past conversation transcripts) which can expose sensitive data to the memory index and any embedding provider, and it instructs restarting the gateway via 'clawdbot gateway restart' which performs an operational action that should be run intentionally by the user.
Install Mechanism
No install spec or code files — instruction-only — so nothing will be downloaded or written to disk by an installer step. This is the lowest install-surface risk.
Credentials
The notes tell users to set VOYAGE_API_KEY and OPENAI_API_KEY for provider errors, but the skill metadata does not declare any required environment variables or a primary credential. That mismatch reduces transparency. Requiring embedding API keys would be proportionate to the task, but they should be declared in the skill manifest so users know up-front what secrets are needed.
Persistence & Privilege
always:false (not force-included) and no persistent install actions are requested. However, the instructions explicitly direct editing agent config files and restarting the gateway; if you allow autonomous agent actions, the agent could apply these changes without further manual approval. Consider whether the agent has permission to modify those files or restart services in your environment.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install chen-memory-setup
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /chen-memory-setup 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the chen-memory-setup skill for Moltbot/Clawdbot. - Helps users enable and configure persistent memory search to improve agent context retention. - Provides step-by-step setup for MEMORY.md, memory directory structure, and recommended config options. - Includes troubleshooting tips for memory search, provider API keys, and context retrieval. - Offers sample agent instructions to integrate memory search behaviors.
元数据
Slug chen-memory-setup
版本 1.0.0
许可证 MIT-0
累计安装 2
当前安装数 1
历史版本数 1
常见问题

Chen Memory Setup 是什么?

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure m... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 116 次。

如何安装 Chen Memory Setup?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install chen-memory-setup」即可一键安装,无需额外配置。

Chen Memory Setup 是免费的吗?

是的,Chen Memory Setup 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Chen Memory Setup 支持哪些平台?

Chen Memory Setup 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Chen Memory Setup?

由 cs995279497-byte(@cs995279497-byte)开发并维护,当前版本 v1.0.0。

💬 留言讨论