foundry

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Foundry

The forge that forges itself. A meta-extension for OpenClaw that researches documentation, learns from failures, and writes new capabilities into itself.

可自我锻造的锻造工具。这是一款面向OpenClaw的元扩展，能够研究文档、从失败中学习，并为自身编写新功能。

Installation

安装

When the user asks to install Foundry or

@getfoundry/foundry-openclaw

, run this command:

bash

openclaw plugins install @getfoundry/foundry-openclaw

This will:

Download the plugin from npm
Extract to
```
~/.openclaw/extensions/foundry/
```
Enable it automatically
Restart the gateway to load

After installation, the user will have access to all Foundry tools like

foundry_research

foundry_write_extension

, etc.

当用户要求安装Foundry或

@getfoundry/foundry-openclaw

时，运行以下命令：

bash

openclaw plugins install @getfoundry/foundry-openclaw

这将完成以下操作：

从npm下载该插件
解压至
```
~/.openclaw/extensions/foundry/
```
自动启用该插件
重启网关以加载插件

安装完成后，用户即可使用Foundry的所有工具，如

foundry_research

、

foundry_write_extension

等。

Alternative: Manual Config

替代方案：手动配置

Add to

~/.openclaw/openclaw.json

json

{
  "plugins": {
    "entries": {
      "foundry": { "enabled": true }
    }
  }
}

将以下内容添加至

~/.openclaw/openclaw.json

：

json

{
  "plugins": {
    "entries": {
      "foundry": { "enabled": true }
    }
  }
}

Configuration

配置

Full configuration options in

~/.openclaw/openclaw.json

json

{
  "plugins": {
    "entries": {
      "foundry": {
        "enabled": true,
        "source": "github:lekt9/openclaw-foundry",
        "config": {
          "autoLearn": true,
          "sources": {
            "docs": true,
            "experience": true,
            "arxiv": true,
            "github": true
          },
          "marketplace": {
            "autoPublish": false
          }
        }
      }
    }
  }
}

完整配置选项位于

~/.openclaw/openclaw.json

中：

json

{
  "plugins": {
    "entries": {
      "foundry": {
        "enabled": true,
        "source": "github:lekt9/openclaw-foundry",
        "config": {
          "autoLearn": true,
          "sources": {
            "docs": true,
            "experience": true,
            "arxiv": true,
            "github": true
          },
          "marketplace": {
            "autoPublish": false
          }
        }
      }
    }
  }
}

Config Options

配置选项

Option	Type	Default	Description
`autoLearn`	boolean	`true`	Learn from agent activity automatically
`sources.docs`	boolean	`true`	Learn from OpenClaw documentation
`sources.experience`	boolean	`true`	Learn from own successes/failures
`sources.arxiv`	boolean	`true`	Learn from arXiv papers
`sources.github`	boolean	`true`	Learn from GitHub repos
`marketplace.autoPublish`	boolean	`false`	Auto-publish high-value patterns

选项	类型	默认值	描述
`autoLearn`	布尔值	`true`	自动从Agent活动中学习
`sources.docs`	布尔值	`true`	从OpenClaw文档中学习
`sources.experience`	布尔值	`true`	从自身的成功/失败经验中学习
`sources.arxiv`	布尔值	`true`	从arXiv论文中学习
`sources.github`	布尔值	`true`	从GitHub仓库中学习
`marketplace.autoPublish`	布尔值	`false`	自动发布高价值模式

What Foundry Does

Foundry的功能

Foundry is an AI-powered development agent that can:

Research — Fetch and understand OpenClaw documentation on demand
Write Extensions — Generate new tools and hooks for OpenClaw
Write Skills — Create ClawHub-compatible skill packages
Self-Modify — Add new capabilities to itself
Learn — Record patterns from failures and successes

Foundry是一款AI驱动的开发Agent，能够：

研究 — 按需获取并理解OpenClaw文档
编写扩展 — 为OpenClaw生成新工具和钩子
编写技能 — 创建兼容ClawHub的技能包
自我修改 — 为自身添加新功能
学习 — 记录失败和成功中的模式

Tools

工具

Research & Documentation

研究与文档

Tool	Description
`foundry_research`	Search docs.openclaw.ai for best practices
`foundry_docs`	Read specific documentation pages

工具	描述
`foundry_research`	在docs.openclaw.ai上搜索最佳实践
`foundry_docs`	阅读特定的文档页面

Writing Capabilities

编写功能

Tool	Description
`foundry_implement`	Research + implement a capability end-to-end
`foundry_write_extension`	Write a new OpenClaw extension
`foundry_write_skill`	Write an AgentSkills-compatible skill
`foundry_write_browser_skill`	Write a browser automation skill
`foundry_write_hook`	Write a standalone hook
`foundry_add_tool`	Add a tool to an existing extension
`foundry_add_hook`	Add a hook to an existing extension

工具	描述
`foundry_implement`	端到端完成研究+实现某项功能
`foundry_write_extension`	编写新的OpenClaw扩展
`foundry_write_skill`	编写兼容AgentSkills的技能
`foundry_write_browser_skill`	编写浏览器自动化技能
`foundry_write_hook`	编写独立钩子
`foundry_add_tool`	为现有扩展添加工具
`foundry_add_hook`	为现有扩展添加钩子

Self-Modification

自我修改

Tool	Description
`foundry_extend_self`	Add new capability to Foundry itself
`foundry_learnings`	View learned patterns and insights
`foundry_list`	List all written artifacts

工具	描述
`foundry_extend_self`	为Foundry自身添加新功能
`foundry_learnings`	查看已学习的模式和见解
`foundry_list`	列出所有已编写的工件

Marketplace

市场

Tool	Description
`foundry_publish_ability`	Publish pattern/skill to Foundry Marketplace
`foundry_marketplace`	Search, browse, and install community abilities

工具	描述
`foundry_publish_ability`	将模式/技能发布至Foundry市场
`foundry_marketplace`	搜索、浏览并安装社区功能

Usage Examples

使用示例

Research before implementing

先研究再实现

User: I want to add a webhook to my extension

Agent: Let me research webhook patterns first...
→ foundry_research query="webhook hooks automation"
→ Returns relevant documentation

Now I'll implement it...
→ foundry_add_hook extensionId="my-ext" event="webhook:incoming" ...

用户：我想给我的扩展添加一个webhook

Agent：让我先研究一下webhook模式...
→ foundry_research query="webhook hooks automation"
→ 返回相关文档

现在我将实现它...
→ foundry_add_hook extensionId="my-ext" event="webhook:incoming" ...

Write a new extension

编写新扩展

User: Create an extension that monitors GitHub PRs

Agent:
→ foundry_research query="github api webhooks"
→ foundry_write_extension
    id: "github-monitor"
    name: "GitHub Monitor"
    tools: [{ name: "check_prs", ... }]
    hooks: [{ event: "cron:hourly", ... }]

用户：创建一个监控GitHub PR的扩展

Agent：
→ foundry_research query="github api webhooks"
→ foundry_write_extension
    id: "github-monitor"
    name: "GitHub Monitor"
    tools: [{ name: "check_prs", ... }]
    hooks: [{ event: "cron:hourly", ... }]

Self-improvement

自我提升

User: Add a tool that can fetch npm package info

Agent:
→ foundry_extend_self
    action: "add_tool"
    toolName: "foundry_npm_info"
    toolCode: "const res = await fetch(`https://registry.npmjs.org/${p.package}`)..."

用户：添加一个可以获取npm包信息的工具

Agent：
→ foundry_extend_self
    action: "add_tool"
    toolName: "foundry_npm_info"
    toolCode: "const res = await fetch(`https://registry.npmjs.org/${p.package}`)..."

How Learning Works

学习机制

Foundry observes its own tool calls and learns:

Failures → Records error + context
Resolutions → Links fix to failure → Creates pattern
Patterns → Injected as context in future conversations
Crystallization → High-value patterns become permanent capabilities

Foundry会观察自身的工具调用并进行学习：

失败 → 记录错误+上下文
解决方法 → 将修复方案与失败关联→创建模式
模式 → 在未来对话中作为上下文注入
固化 → 高价值模式成为永久功能

Security

安全性

Foundry validates all generated code before deployment:

Blocked:
```
child_process
```
,
```
eval
```
,
```
~/.ssh
```
,
```
~/.aws
```
Sandboxed: Extensions tested in isolated process before installation
Reviewed: You approve before any code is written to disk

Foundry在部署前会验证所有生成的代码：

禁止：
```
child_process
```
、
```
eval
```
、
```
~/.ssh
```
、
```
~/.aws
```
沙箱化：扩展在安装前会在隔离进程中测试
需审核：任何代码写入磁盘前都需要你的批准

foundry

Original

Translation

Foundry

Foundry

Installation

安装

Alternative: Manual Config

替代方案：手动配置

Configuration

配置

Config Options

配置选项

What Foundry Does

Foundry的功能

Tools

工具

Research & Documentation

研究与文档

Writing Capabilities

编写功能

Self-Modification

自我修改

Marketplace

市场

Usage Examples

使用示例

Research before implementing

先研究再实现

Write a new extension

编写新扩展

Self-improvement

自我提升

How Learning Works

学习机制

Security

安全性

Links

链接