# Agent Foundry: A Unified Management Tool for Cross-Platform AI Agent Plugin Ecosystem

> Agent Foundry is an open-source AI Agent plugin registry and CLI tool that supports installing unified plugins across multiple AI coding assistant platforms including Codex, Claude Code, Cursor, and Copilot, solving the configuration management challenges caused by the fragmentation of AI tools.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-02T21:45:03.000Z
- 最近活动: 2026-05-03T01:39:36.335Z
- 热度: 160.1
- 关键词: Agent Foundry, AI Agent, 插件管理, 跨平台, Codex, Claude Code, Cursor, Copilot, MCP, AI编程助手
- 页面链接: https://www.zingnex.cn/en/forum/thread/agent-foundry-ai-agent
- Canonical: https://www.zingnex.cn/forum/thread/agent-foundry-ai-agent
- Markdown 来源: floors_fallback

---

## Agent Foundry: A Unified Management Tool for Cross-Platform AI Agent Plugins

Agent Foundry is an open-source AI Agent plugin registry and CLI tool that supports installing unified plugins across multiple AI coding assistant platforms (Codex, Claude Code, Cursor, Copilot etc.). It addresses the configuration management challenges caused by the fragmentation of AI tool ecosystems, allowing developers to write plugins once and use them across platforms.

## The Fragmentation Dilemma of AI Coding Assistant Ecosystems

Mainstream AI coding assistants have independent extension mechanisms:
- OpenAI Codex uses `.codex/plugins/` directory and `marketplace.json`.
- Claude Code uses `.claude/` directory and supports MCP (Model Context Protocol) servers.
- Cursor provides IDE plugins and CLI with different path configurations.
- GitHub Copilot CLI only supports user-level configuration.
This fragmentation leads to repeat work, scattered configurations, migration difficulties, and isolated plugin ecosystems.

## Core Design of Agent Foundry: One Write, Multi-Platform Use

Agent Foundry's core design includes:
1. **Unified Plugin Format**: Plugins stored in `plugins/` directory with `plugin.yaml` (metadata), `skills/` (reusable skill definitions), `agents/` (complete agent definitions), and `mcp/` (MCP server configs).
2. **Registry Mechanism**: `registry/plugins.yaml` as a central index for plugin discovery, version management, and dependency resolution.
3. **Cross-Platform Adaptation**: CLI automatically handles platform differences (paths, special processing like soft links or config merging) during installation.

## Agent Foundry CLI: Installation & Usage Guide

**Install CLI**: Use `pipx install git+https://github.com/josemiguelmelo/agent-foundry.git` (recommended) or source installation.
**Install Plugins**: Global (e.g., `agent-foundry install codex code-reviewer`), project-level (add `--in-project`), or local repo (add `--repo` path).
**Manage Plugins**: Uninstall (e.g., `agent-foundry uninstall codex code-reviewer`), validate registry (`agent-foundry validate-plugins`), or check help (`agent-foundry --help`).
**Develop Plugins**: Create skeleton (`agent-foundry create-plugin my-awesome-plugin`), remove plugin (`agent-foundry remove-plugin my-awesome-plugin`).

## Best Practices for Agent Foundry Plugin Development

**Skill Design Principles**: Clear trigger conditions, focused职责, configurable parameters, and complete examples.
**Agent Orchestration Patterns**: Pipeline (doc→code→test→review), decision tree (based on complexity), multi-expert会诊 (parallel reviews by specialized agents).
**MCP Integration**: Support tool discovery, state management, and security boundaries as per Anthropic's Model Context Protocol standard.

## Practical Application Scenarios of Agent Foundry

- **Team Standardization**: Centralize AI configurations, unify code review standards, and share project knowledge.
- **Open Source Contribution**: Lower barriers with project-specific guide agents, PR规范 checks, and interactive onboarding.
- **Personal Workflow**: Reuse prompts/skills across projects and experiment with new AI workflows.

## Limitations & Future Roadmap of Agent Foundry

**Current Limitations**: Platform ability differences, Claude Code's lack of project-level installation, Copilot's closed ecosystem restrictions, and version compatibility issues.
**Future Plans**: Support more tools (Continue.dev, Aider, Supermaven), build a community plugin market, provide a GUI editor, add automation testing, and enable cloud sync for plugin configurations.

## Agent Foundry vs. Similar Tools: Unique Value Proposition

| Feature | Agent Foundry | Promptfoo | LangChain CLI |
|---------|---------------|-----------|---------------|
| Goal | Multi-platform plugin management | Prompt testing & evaluation | Application development framework |
| Supported Platforms | Codex/Claude/Cursor/Copilot | General | Custom applications |
| Plugin Format | Standard YAML | Any text | Python code |
| Ease of Use | High (CLI-driven) | Medium | Low (requires programming) |
Agent Foundry's unique value: It bridges existing AI tools instead of replacing them, solving the 'last mile' interoperability problem.