# Open Dynamic Workflow: An Open-Source Alternative to Claude Code's Dynamic Workflow, Supporting Multi-Model and Deterministic Recovery

> Open Dynamic Workflow is an open-source reimplementation of Claude Code's built-in Dynamic Workflow. Through a decoupled design of the orchestration layer and execution layer, it supports multiple LLM runtimes, Git worktree isolation, deterministic recovery, and offline execution reports.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-06-02T23:45:04.000Z
- 最近活动: 2026-06-02T23:51:08.168Z
- 热度: 154.9
- 关键词: Claude Code, Dynamic Workflow, 开源工作流, 多模型编排, Rust, 国产LLM, git工作树, 确定性恢复, AI代理, 成本优化
- 页面链接: https://www.zingnex.cn/en/forum/thread/open-dynamic-workflow-claude-code
- Canonical: https://www.zingnex.cn/forum/thread/open-dynamic-workflow-claude-code
- Markdown 来源: floors_fallback

---

## Open Dynamic Workflow: Open-Source Alternative to Claude Code's Dynamic Workflow

Open Dynamic Workflow (odw) is an open-source reimplementation of Claude Code's built-in Dynamic Workflow, addressing limitations of the original black-box system. Key features: 
- Multi-LLM runtime support (including domestic models like DeepSeek, Kimi, Qwen)
- Git worktree isolation for parallel tasks
- Deterministic crash recovery
- Offline execution reports
- Decoupled orchestration/execution layers
Written in Rust, licensed under MIT for broad adoption.

## Background: Why Odw Was Created

Claude Code's built-in Dynamic Workflow lacks self-hosting, engine customization, precise model tracking, and crash recovery—critical gaps for enterprise scenarios. Odw was built as an open-source alternative with enterprise-grade features, split into two Rust crates for orchestration and execution.

## Architecture: Decoupled Orchestration & Execution

Odw’s core components: 
1. **odw crate**: Orchestrates workflows (primitives like agent/parallel/pipeline), manages budgets, git isolation, recovery, and dispatches tasks.
2. **pandacode crate**: Executes tasks via Codex, Claude, or domestic LLMs (Bamboo runtime: DeepSeek, Kimi, Qwen, Zhipu, Minimax).
Components are independent—replace executors without changing orchestration logic.

## Core Features of Odw

Odw’s key features: 
- Full workflow primitives (agent, parallel, pipeline, phase, budget, nested workflows)
- Multi-runtime per node (Codex/Claude/domestic LLMs)
- Git worktree isolation for parallel task conflict avoidance
- Deterministic recovery via journal logs
- Offline report.html with Mermaid charts (node details: model, tokens, time, prompts)

## Cost Benefits: Heterogeneous Models Save Expenses

Cost comparison: 12-node workflow uses ~79k tokens (odw: mixed domestic + Claude) vs ~252k tokens (built-in: pure Claude)—1/3 cost. Reasons: 
1. Cheaper domestic models for simple tasks
2. Lighter odw nodes vs full Claude sub-agents
Stable for 100 parallel nodes (concurrency: min(16, cores-2)).

## Use Cases & Tradeoffs

**Tradeoffs**: 
- Built-in: Zero config, full Claude sub-agents, session monitoring.
- Odw: Cost savings, offline observability, crash recovery, self-hosting/headless.
**Odw use cases**: Cost-sensitive, offline reporting, crash recovery, self-hosted scenarios.

## Installation & Usage

**Installation**: Clone repo → run install.sh (adds odw/pandacode to PATH). Use `odw doctor` to verify environment.
**Usage**: 
- JS workflows (same syntax as built-in)
- `odw init`: Generate project files
- `odw exec --backend mock`: Dry run
- Claude Code users: Dedicated skill file (.claude/skills/odw/SKILL.md) for agent guidance.