Leeway工作流AI智能体 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.2 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
Leeway工作流AI智能体 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Leeway工作流AI智能体 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排，将复杂的多步骤任务拆解为清晰的自动化流程，实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成，适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一：pip 安装（推荐）
pip install leeway
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install leeway
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/hardness1020/Leeway
cd Leeway
pip install -e .
# 验证安装
python -c "import leeway; print('安装成功')"
# 命令行使用
leeway --help
# 基本用法
leeway input_file -o output_file
# Python 代码中调用
import leeway
# 示例
result = leeway.process("input")
print(result)
# leeway 配置文件示例（config.yml） app: name: "leeway" debug: false log_level: "INFO" # 运行时指定配置文件 leeway --config config.yml # 或通过环境变量配置 export LEEWAY_API_KEY="your-key" export LEEWAY_OUTPUT_DIR="./output"
<p align="center" style="margin-bottom: 0;"> <video src="https://github.com/user-attachments/assets/fda824d3-0102-44eb-836b-42d3dd5d062f" autoplay loop muted playsinline width="1000"></video> </p>
<p align="center"> <strong>Human-defined workflows. AI-powered execution.</strong><br> YAML decision trees with scheduling, hooks, MCP, and 21 built-in tools. </p>
<p align="center"> <a href="#-quick-start"><img src="https://img.shields.io/badge/Quick_Start-3_min-blue?style=for-the-badge" alt="Quick Start"></a> <a href="guides/workflows.md"><img src="https://img.shields.io/badge/Workflows-YAML-ff69b4?style=for-the-badge" alt="Workflows"></a> <a href="guides/tools.md"><img src="https://img.shields.io/badge/Tools-21+-green?style=for-the-badge" alt="Tools"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge" alt="License"></a> </p>
<p align="center"> <img src="https://img.shields.io/badge/python-≥3.10-blue?logo=python&logoColor=white" alt="Python"> <img src="https://img.shields.io/badge/React+Ink-TUI-61DAFB?logo=react&logoColor=white" alt="React"> <img src="https://img.shields.io/badge/output-text_|json|_stream--json-blueviolet" alt="Output"> </p>
---
Five things that are hard to get from a node-graph workflow tool:
| # | Feature | What it does |
|---|---|---|
| 1 | **Agent loop per node** | Each node is a full agent loop. The model can call read_file, grep, bash, iterate up to max_turns, and emit a workflow_signal when done. You decide the graph; the model decides the steps within each node. |
| 2 | **Per-node scoping** | Every node gets its own ToolRegistry, SkillRegistry, HookRegistry, and MCP set, merged from globals and the node's allowlist. Node A can have bash + glob; node B can have web_fetch + mcp_github_search; same workflow. |
| 3 | **Progressive skill loading, per node** | skill(name="code-review") returns SKILL.md plus a file index. Reference files load only when the LLM explicitly asks. Combined with per-node scoping, each node only sees its allowlisted skills, and only their top-level content until the model drills in. |
| 4 | **Turn budget with urgency injection** | For signal-based nodes, the engine tells the LLM how many turns it has and injects an *urgent reminder* at 2 turns remaining, listing the exact signals to call. No silent cost runaway. |
| 5 | **Auto-compaction (microcompact + LLM summary)** | When context fills, Leeway first clears stale tool-result bodies in place. If that's not enough, it summarizes older messages via LLM while preserving the last 6. Fully transparent: no manual /compact, no lost context mid-workflow. |
```bash
git clone https://github.com/your-org/Leeway.git cd Leeway uv sync --extra dev
```bash
uv run leeway > /code-health start ```
<p align="center"> <img src="assets/workflow_interactive.png" alt="Interactive workflow execution" width="1000"> </p>
---
See .leeway/workflows/code-health.yaml. It covers all five patterns (linear, branch, loop, terminal, parallel) in one workflow with skills, hooks, and approval gates.
> /workflows<p align="center"> <img src="assets/workflow_graph.png" alt="Code-health workflow graph" width="1000"> </p>
export ANTHROPIC_API_KEY=sk-...
<p align="center"> <img src="assets/workflow_process.png" alt="Workflow execution progress" width="1000"> </p>
See guides/workflows.md for the full pattern catalog and every property table.
---
| Who drives the flow? | What's in a node? | Best for | |
|---|---|---|---|
| **AutoGPT, OpenClaw** | LLM | Whatever the LLM decides | Exploratory tasks |
| **n8n** | Graph | Any kind of node (API call, transform, AI Agent subflow) | Connecting SaaS APIs (Slack, Stripe, Airtable) |
| **Leeway** | Graph (decisions) | A full agent loop with local-dev tools | Personal workflows and custom engineering pipelines that plug into your own system (files, shell, codebase) |
n8n is incredible for connecting SaaS APIs. Leeway is built specifically for personal workflows and custom engineering pipelines that integrate directly into your own system: your files, your shell, your repo, not third-party webhooks.
Pick Leeway when the task runs on your own files or shell, needs to be repeatable, and needs a model that can reason inside each step.
---
Leeway提供了YAML驱动的工作流框架，适合构建结构化AI智能体系统。决策树设计理念清晰，人机协作功能实用，但社区规模小，文档完善度待考察。
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
经综合评估，Leeway工作流AI智能体 在Agent工作流赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | Leeway |
| 原始描述 | 开源AI工作流：A workflow-driven AI agent framework that executes YAML-defined decision trees.。⭐109 · Python |
| Topics | 工作流AI智能体决策树YAML配置人机协作 |
| GitHub | https://github.com/hardness1020/Leeway |
| License | MIT |
| 语言 | Python |
收录时间：2026-05-21 · 更新时间：2026-05-22 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型，复制安装指令后粘贴到对应客户端