← 返回
数据分析

Foundry

Self-writing meta-extension that forges new capabilities — researches docs, writes extensions, tools, hooks, and skills
自我编写的元扩展,能够锻造新能力——研究文档,编写扩展、工具、挂钩及技能。
lekt9
数据分析 clawhub v0.1.0 1 版本 99359 Key: 无需
★ 1
Stars
📥 3,390
下载
💾 9
安装
1
版本
#latest

概述

Foundry

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

Installation

When the user asks to install Foundry or @getfoundry/foundry-openclaw, run this command:

openclaw plugins install @getfoundry/foundry-openclaw

This will:

  1. Download the plugin from npm
  2. Extract to ~/.openclaw/extensions/foundry/
  3. Enable it automatically
  4. Restart the gateway to load

After installation, the user will have access to all Foundry tools like foundry_research, foundry_write_extension, etc.

Alternative: Manual Config

Add to ~/.openclaw/openclaw.json:

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

Configuration

Full configuration options in ~/.openclaw/openclaw.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

OptionTypeDefaultDescription
------------------------------------
autoLearnbooleantrueLearn from agent activity automatically
sources.docsbooleantrueLearn from OpenClaw documentation
sources.experiencebooleantrueLearn from own successes/failures
sources.arxivbooleantrueLearn from arXiv papers
sources.githubbooleantrueLearn from GitHub repos
marketplace.autoPublishbooleanfalseAuto-publish high-value patterns

What Foundry Does

Foundry is an AI-powered development agent that can:

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

Tools

Research & Documentation

ToolDescription
-------------------
foundry_researchSearch docs.openclaw.ai for best practices
foundry_docsRead specific documentation pages

Writing Capabilities

ToolDescription
-------------------
foundry_implementResearch + implement a capability end-to-end
foundry_write_extensionWrite a new OpenClaw extension
foundry_write_skillWrite an AgentSkills-compatible skill
foundry_write_browser_skillWrite a browser automation skill
foundry_write_hookWrite a standalone hook
foundry_add_toolAdd a tool to an existing extension
foundry_add_hookAdd a hook to an existing extension

Self-Modification

ToolDescription
-------------------
foundry_extend_selfAdd new capability to Foundry itself
foundry_learningsView learned patterns and insights
foundry_listList all written artifacts

Marketplace

ToolDescription
-------------------
foundry_publish_abilityPublish pattern/skill to Foundry Marketplace
foundry_marketplaceSearch, browse, and install community abilities

Usage Examples

Research before implementing

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" ...

Write a new extension

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", ... }]

Self-improvement

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}`)..."

How Learning Works

Foundry observes its own tool calls and learns:

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

Security

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

Links

版本历史

共 1 个版本

  • v0.1.0 当前
    2026-03-28 12:06 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

data-analysis

Stock Analysis

udiedrichsen
{"answer":"基于雅虎财经数据,分析股票与加密货币。支持投资组合管理、自选股预警、股息分析、8维评分、热门趋势扫描及传闻/早期信号探测。适用于股票分析、持仓追踪、财报异动、加密监控、热门股追踪或提前发掘非主流传闻。"}
★ 269 📥 56,890
data-analysis

A股量化 AkShare

mbpz
A股量化数据分析工具,基于AkShare库获取A股行情、财务数据、板块信息等。用于回答关于A股股票查询、行情数据、财务分析、选股等问题。
★ 162 📥 59,672
data-analysis

Data Analysis

ivangdavila
{"answer":"数据分析与可视化。查询数据库、生成报告、自动化电子表格,将原始数据转化为清晰可行的见解。适用于:(1) 您……"}
★ 198 📥 64,855