# AgentLoom: A Deterministic Multi-Agent Workflow Orchestration Engine Based on OpenCode > AgentLoom is a self-hosted multi-agent workflow runner compatible with Claude Code's dynamic workflow API. Built on OpenCode, it supports deterministic AI workflow execution, sub-agent fan-out, custom tool registration, prompt caching optimization, and features a real-time Web UI that displays tokens and tool calls for each running agent. - 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm) - 发布时间: 2026-05-28T18:45:11.000Z - 最近活动: 2026-05-28T18:52:04.305Z - 热度: 123.9 - 关键词: AgentLoom, 多智能体, 工作流编排, OpenCode, AI工作流, Claude Code, MCP, 提示词缓存 - 页面链接: https://www.zingnex.cn/en/forum/thread/agentloom-opencode - Canonical: https://www.zingnex.cn/forum/thread/agentloom-opencode - Markdown 来源: floors_fallback --- ## Introduction / Main Post: AgentLoom: A Deterministic Multi-Agent Workflow Orchestration Engine Based on OpenCode AgentLoom is a self-hosted multi-agent workflow runner compatible with Claude Code's dynamic workflow API. Built on OpenCode, it supports deterministic AI workflow execution, sub-agent fan-out, custom tool registration, prompt caching optimization, and features a real-time Web UI that displays tokens and tool calls for each running agent. ## Original Author and Source - Original Author/Maintainer: vblanco20-1 - Source Platform: GitHub - Original Title: AgentLoom - Original Link: https://github.com/vblanco20-1/AgentLoom - Source Publication/Update Time: 2026-05-28T18:45:11Z ## Original Author and Source - **Original Author/Maintainer**: vblanco20-1 - **Source Platform**: GitHub - **Original Title**: AgentLoom: Prototype agentic orchestrator for deterministic AI workflows - **Original Link**: https://github.com/vblanco20-1/AgentLoom - **Publication Time**: May 28, 2026 --- ## Project Background and Positioning With the rapid advancement of Large Language Model (LLM) capabilities, AI system architectures based on Agents are emerging. From single-agent conversations to multi-agent collaboration, from simple task execution to complex workflow orchestration, developers need more powerful tools to manage and coordinate these AI workflows. AgentLoom was born to address this need. It is a self-hosted multi-agent workflow runner whose API design is fully compatible with Claude Code's dynamic workflow features. This means developers can run workflow scripts that originally relied on the Claude Code client in a local environment, gaining greater flexibility and control. The core positioning of the project is: to provide a deterministic, reproducible, and observable AI workflow execution engine, enabling developers to build complex agent collaboration systems while maintaining full control over the execution process. --- ## Relationship with Claude Code's Dynamic Workflow AgentLoom has a direct lineage with Claude Code's dynamic workflow feature. As an AI programming assistant launched by Anthropic, Claude Code has a built-in powerful workflow system that supports AI to automatically generate and execute multi-step tasks through natural language descriptions. AgentLoom implements the same API surface, including: - **Same globally injected variables**: `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `args` - **Same metadata export format**: `meta = { name, description, phases }` - **Same schema validation mechanism**: Agent return results undergo JSON schema validation - **Same non-blocking pipeline semantics**: `pipeline()` stages use streaming processing instead of waiting for all to complete - **Same background execution model**: Workflows run in the background, supporting pause and resume The main differences between the two are: | Feature | Claude Code Dynamic Workflow | AgentLoom | ## Supplementary Viewpoint 1 Original Author and Source - Original Author/Maintainer: vblanco20-1 - Source Platform: GitHub - Original Title: AgentLoom - Original Link: https://github.com/vblanco20-1/AgentLoom - Source Publication/Update Time: 2026-05-28T18:45:11Z - **Original Author/Maintainer**: vblanco20-1 - **Source Platform**: GitHub - **Original Title**: AgentLoom: Prototype agentic orchestrator for deterministic AI workflows - **Original Link**: https://github.com/vblanco20-1/AgentLoom - **Publication Time**: May 28, 2026 --- Project Background and Positioning With the rapid advancement of Large Language Model (LLM) capabilities, AI system architectures based on Agents are emerging. From single-agent conversations to multi-agent collaboration, from simple task execution to complex workflow orchestration, developers need more powerful tools to manage and coordinate these AI workflows. AgentLoom was born to address this need. It is a self-hosted multi-agent workflow runner whose API design is fully compatible with Claude Code's dynamic workflow features. This means developers can run workflow scripts that originally relied on the Claude Code client in a local environment, gaining greater flexibility and control. The core positioning of the project is: to provide a deterministic, reproducible, and observable AI workflow execution engine, enabling developers to build complex agent collaboration systems while maintaining full control over the execution process. --- Relationship with Claude Code's Dynamic Workflow AgentLoom has a direct lineage with Claude Code's dynamic workflow feature. As an AI programming assistant launched by Anthropic, Claude Code has a built-in powerful workflow system that supports AI to automatically generate and execute multi-step tasks through natural language descriptions. AgentLoom implements the same API surface, including: - **Same globally injected variables**: `agent()`, `pipeline()`, `parallel()`, `phase()`, `log()`, `args` - **Same metadata export format**: `meta = { name, description, phases }` - **Same schema validation mechanism**: Agent return results undergo JSON schema validation - **Same non-blocking pipeline semantics**: `pipeline()` stages use streaming processing instead of waiting for all to complete - **Same background execution model**: Workflows run in the background, supporting pause and resume The main differences between the two are: | Feature | Claude Code Dynamic Workflow | AgentLoom |