← 返回 Skills 市场
gwsq

Memory Setup 1.0.0

作者 Gwsq · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
415
总下载
0
收藏
23
当前安装
1
版本数
在 OpenClaw 中安装
/install memory-setup-1-0-0
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 persistent memory), but it references external API keys and edits config files without declaring those secrets in the metadata. Before following instructions or providing keys: 1) Verify what 'voyage' is (official site, privacy terms, where embeddings go). 2) Prefer the 'local' provider if you don't want data sent to third parties. 3) Do not paste API keys into shared files or public repos; store them in a secure place. 4) Back up ~/.clawdbot/clawdbot.json and workspace memory files before editing. 5) Be mindful that MEMORY.md and daily logs may contain sensitive data — assess privacy risk of indexing them. If you need higher assurance, ask the skill author for provenance of the 'voyage' provider and update the skill metadata to declare required env vars before use.
功能分析
Type: OpenClaw Skill Name: memory-setup-1-0-0 Version: 1.0.0 The skill bundle is purely informational, providing documentation and configuration templates for enabling persistent memory features in Moltbot/Clawdbot. It contains no executable code, and the instructions in SKILL.md are transparently aligned with its stated purpose of setting up memory search and directory structures.
能力评估
Purpose & Capability
Name and description align with the instructions: the SKILL.md describes enabling memorySearch, creating MEMORY.md and memory/ files, and configuring the agent. The operations and files it asks you to create/edit are coherent with a memory-setup task.
Instruction Scope
The instructions explicitly tell users/agents to edit ~/.clawdbot/clawdbot.json (or moltbot.json), workspace files, and to run 'clawdbot gateway restart'. They also reference runtime actions for agents (memory_search, memory_get). These are within scope, but the SKILL.md also mentions environment variables (VOYAGE_API_KEY, OPENAI_API_KEY) that are not declared in the skill metadata — the skill instructs the agent/user to set secrets without declaring them. That mismatch should be noted before granting access or following the instructions.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so it does not download or write executables. That minimizes installation risk.
Credentials
The SKILL.md recommends setting VOYAGE_API_KEY and OPENAI_API_KEY (and suggests using a third-party 'voyage' provider) but the skill's metadata lists no required environment variables or primary credential. The instructions therefore expect secrets that the registry metadata doesn't declare. This is a transparency gap and increases risk because the skill may prompt you to create/store API keys for an external provider.
Persistence & Privilege
The skill does not request always:true and does not modify other skills' configs. It only instructs how to edit user config files and workspace files, which is expected for a setup guide. Autonomous invocation is allowed by default, but there is no indication this skill needs permanent elevated presence.
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 memory-setup-1-0-0
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /memory-setup-1-0-0 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 — enables persistent memory setup and search for Moltbot/Clawdbot agents. - Provides step-by-step instructions for enabling and configuring memory search in config files. - Details recommended workspace memory structure, including MEMORY.md and daily logs. - Explains core config options and embedding providers. - Offers troubleshooting tips for common memory setup issues. - Includes verification steps and best practices for effective agent memory use.
元数据
Slug memory-setup-1-0-0
版本 1.0.0
许可证
累计安装 26
当前安装数 23
历史版本数 1
常见问题

Memory Setup 1.0.0 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 415 次。

如何安装 Memory Setup 1.0.0?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install memory-setup-1-0-0」即可一键安装,无需额外配置。

Memory Setup 1.0.0 是免费的吗?

是的,Memory Setup 1.0.0 完全免费(开源免费),可自由下载、安装和使用。

Memory Setup 1.0.0 支持哪些平台?

Memory Setup 1.0.0 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 Memory Setup 1.0.0?

由 Gwsq(@gwsq)开发并维护,当前版本 v1.0.0。

💬 留言讨论