# Iso: Cross-Platform AI Agent Toolchain, Write Once, Run Anywhere

> Iso, an open-source project by Razroo, is a complete AI agent development toolchain. Through 14 collaborative npm packages, it addresses three key issues: tool fragmentation, model capability differences, and runtime reliability, enabling a single set of instructions to run seamlessly across multiple platforms like Claude Code, Cursor, Codex, and OpenCode.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-04-26T19:45:04.000Z
- 最近活动: 2026-04-26T19:52:13.438Z
- 热度: 145.9
- 关键词: AI代理, Claude Code, Cursor, Codex, OpenCode, 跨平台, 提示工程, MCP, 代理工作流, Razroo
- 页面链接: https://www.zingnex.cn/en/forum/thread/iso-ai
- Canonical: https://www.zingnex.cn/forum/thread/iso-ai
- Markdown 来源: floors_fallback

---

## Iso: Cross-Platform AI Agent Toolchain, Write Once, Run Anywhere

Iso, an open-source project by Razroo, is a complete AI agent development toolchain. Through 14 collaborative npm packages, it addresses three key issues: tool fragmentation, model capability differences, and runtime reliability, enabling a single set of instructions to run seamlessly across multiple platforms like Claude Code, Cursor, Codex, and OpenCode.

## Background: Three Fragmentation Pain Points in AI Agent Workflows

Current AI programming assistants face three core issues: 1. Tool fragmentation: Different platforms use different configuration formats (e.g., Claude Code uses CLAUDE.md, Cursor uses .cursor/rules/*.mdc, etc.), and maintaining multiple configurations easily leads to drift. 2. Model fragmentation: Prompts for cutting-edge models may silently fail on smaller models. 3. Runtime fragmentation: Relies on fragile prompts to control runtime logic (e.g., fan-out limits, state tracking) and lacks deterministic local package support.

## Methodology: Iso's Collaborative Solution with 14 npm Packages

Iso forms an end-to-end toolchain through 14 npm packages in four categories: 1. Build-time tools (4): @razroo/agentmd (structured prompt dialect), @razroo/isolint (checks compatibility issues with small models), @razroo/iso-harness (translates source directories to platform-specific formats), @razroo/iso-route (model strategy management); 2. Wrapper (1): @razroo/iso (CLI entry point); 3. Runtime control libraries (6): e.g., iso-orchestrator (recoverable steps), iso-context (context management), etc.; 4. Feedback tools (3): iso-eval (task evaluation), iso-trace (session analysis), iso-guard (policy checks).

## Evidence: Platform Support and Quick Start

1. Platform support matrix: Currently supports Claude Code, Codex, OpenCode (full functionality) and Cursor (model binding with only advisory comments); 2. Quick start: After installing @razroo/iso, execute `npx iso build .` to translate source files into multi-platform formats; 3. Small model loop: Through isolint rewriting prompts, iso-route fixing roles, etc., it enables seamless downgrading from cutting-edge model development to small models.

## Application Scenarios and Technical Architecture Highlights

1. Application scenarios: Multi-platform teams (consistent agent behavior), cost optimization (frontend/backend model switching), enterprise compliance (auditable workflows), open-source projects (standardized configurations); 2. Technical highlights: Local-first (no MCP/model dependencies), determinism (key operations reproducible), layered design (modular composition), feedback loop (full process from writing to evaluation).

## Summary and Open-Source Ecosystem

Iso is a standardized AI agent toolchain that does not replace existing tools but promotes collaboration, improving workflow maintainability, portability, and cost-effectiveness. The project is open-sourced on npm, uses Changesets for version management, and provides end-to-end examples (e.g., examples/pipeline/) and dogfood projects.