AI Skill Hub 推荐使用：Crayotter 是一款优质的Agent工作流。AI 综合评分 7.5 分，在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案，这是一个值得深入了解的选择。
Crayotter 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。
Crayotter 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 crayotter
# 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 crayotter
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/idwts/Crayotter
cd Crayotter
pip install -e .
# 验证安装
python -c "import crayotter; print('安装成功')"
# 命令行使用
crayotter --help
# 基本用法
crayotter input_file -o output_file
# Python 代码中调用
import crayotter
# 示例
result = crayotter.process("input")
print(result)
# crayotter 配置文件示例（config.yml） app: name: "crayotter" debug: false log_level: "INFO" # 运行时指定配置文件 crayotter --config config.yml # 或通过环境变量配置 export CRAYOTTER_API_KEY="your-key" export CRAYOTTER_OUTPUT_DIR="./output"
<p align="center"> <a href="./README.md">English</a> | <a href="./README_CN.md">中文</a> </p>
<p align="center"> <img src="./logo.png" alt="Crayotter Logo" width="180" /> </p>
<p align="center"> <a href="https://idwts.github.io/Crayotter" target="_blank" rel="noopener noreferrer"> <img src="https://img.shields.io/badge/🚀-Interactive%20Demo-4CAF50?style=for-the-badge&logo=googlechrome&logoColor=white" alt="Interactive Demo"> </a> <a href="https://github.com/idwts/Crayotter/stargazers" target="_blank" rel="noopener noreferrer"> <img src="https://img.shields.io/github/stars/idwts/Crayotter?style=for-the-badge&logo=github&label=Star%20Crayotter&color=ffb347" alt="Star Crayotter on GitHub"> </a> <a href="https://idwts.github.io/Crayotter/paper/" target="_blank" rel="noopener noreferrer"> <img src="https://img.shields.io/badge/Blog-Paper%20Page-6f7cff?style=for-the-badge" alt="Research Blog"> </a> </p>
<p align="center"> If Crayotter helps your research or demos, please consider giving the repo a Star on GitHub. </p>
Crayotter is a multimodal, agent-driven video editing system that turns a single text request into a complete edited video.
It combines planning, deep editing research, and tool-based execution into a three-phase workflow, with full logs and visual trace analysis for debugging and iteration.
---
<img src="crayottor_framework.jpg">
This repository centers around four core components:
script\agent.py: Main entrypoint. Initializes runtime, runs tasks (interactive or single request), performs workspace cleanup, and writes logs/experience memory.script\graph.py: Orchestration layer (LangGraph StateGraph). Defines the three-phase workflow and routing.script\tools\: Modular toolset for search, download, analysis, cutting, transitions, narration, subtitles, and export.script\visualize.py: Log parser + local trace server for inspecting phase progress and tool calls.Supporting folders:
temp\: Intermediate and output artifacts during execution.user_temp\: User-provided local source assets.logs\: Runtime logs (video_agent_*.log).memory_experience\: Concise historical-case notes kept for reference only; they must not override the current task goal.website\: Static launch site and GitHub Pages assets.---
pip install -r requirements.txtUse Python 3.10+.
python -m venv .venv
.venv\Scripts\activateCopy .env.example to .env, then edit the values there:
copy .env.example .envCommon options:
CRAYOTTER_API_KEY=your-key
CRAYOTTER_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
CRAYOTTER_MODEL_NAME=qwen-plus
CRAYOTTER_VIDEO_MODEL_NAME=qwen-vl-max-latest
CRAYOTTER_TTS_MODEL_NAME=qwen-tts-latest
CRAYOTTER_ENABLE_PHASE2_RESEARCH=true
CRAYOTTER_DIRECT_PHASE3_EXECUTION=false
CRAYOTTER_PREFER_LOCAL_MATERIALS=false
CRAYOTTER_AGENT_STALL_TIMEOUT_SECONDS=150Notes:
CRAYOTTER_DIRECT_PHASE3_EXECUTION=true skips material search/download and goes straight into the existing-material analysis + Phase 3 execution path.CRAYOTTER_PREFER_LOCAL_MATERIALS=true analyzes local materials first and only searches online when the current materials are not enough.CRAYOTTER_AGENT_STALL_TIMEOUT_SECONDS controls the “no new progress” watchdog threshold for running jobs..env.user_temp, Crayotter now writes the matching *_analysis.json back into user_temp, reuses it on later runs, and removes the paired JSON when that upload is deleted from the workbench.memory_experience\latest_skills.md is automatically compacted into bounded, reference-only case notes so it does not grow indefinitely or redefine future task goals.Security note: never commit real API keys to version control.
Crayotter uses a three-phase architecture:
1. Phase 1 — Material Preparation (Planner + Executor) - Search candidate videos - Rank/select high-quality candidates - Download selected videos - Analyze each source video multimodally
2. Phase 2 — Editing Research - Read all analysis outputs - Build a structured editing blueprint (narrative, rhythm, transitions, narration strategy) - No editing tools are called in this phase
This phase can be disabled with CRAYOTTER_ENABLE_PHASE2_RESEARCH=false in the runtime .env to save tokens. When disabled, the workflow becomes: Phase 1 → Phase 3.
3. Phase 3 — ReAct Editing Execution - Execute cutting, merging, transition design, narration/subtitles, and final export - Log full tool-call trajectory for later trace visualization
---
Crayotter 是一个开源的 AI 工作流，提供了视频编辑、视频组合和文本到视频转换的功能，虽然代码质量较高，但仍需要进一步优化和完善。
该工具未明确声明开源协议，商业使用前请联系原作者确认授权范围，避免侵权风险。
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。
总体来看，Crayotter 是一款质量良好的Agent工作流，在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态，建议收藏备用，结合自身场景选择合适时机引入使用。
| 原始名称 | Crayotter |
| Topics | workflowai-agentmllmstext-to-videovideo-composingvideo-editingpython |
| GitHub | https://github.com/idwts/Crayotter |
| 语言 | Python |
收录时间：2026-05-24 · 更新时间：2026-05-24 · License：未公布 · 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