经 AI Skill Hub 精选评估,SeeReel 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
SeeReel是开源AI工作流,Agent-native Seedance 2.0短片工作室:cli为AI,canvas为人类。它提供了一个易于使用的界面,允许用户创建和管理AI工作流。
SeeReel 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。
SeeReel是开源AI工作流,Agent-native Seedance 2.0短片工作室:cli为AI,canvas为人类。它提供了一个易于使用的界面,允许用户创建和管理AI工作流。
SeeReel 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:npm 全局安装 npm install -g seereel # 方式二:npx 直接运行(无需安装) npx seereel --help # 方式三:项目依赖安装 npm install seereel # 方式四:从源码运行 git clone https://github.com/feifeibear/SeeReel cd SeeReel npm install npm start
# 命令行使用
seereel --help
# 基本用法
seereel [options] <input>
# Node.js 代码中使用
const seereel = require('seereel');
const result = await seereel.run(options);
console.log(result);
# seereel 配置说明 # 查看配置选项 seereel --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export SEEREEL_CONFIG="/path/to/config.yml"
<p align="center"> <img src="docs/seereel-logo.png" alt="SeeReel" width="360" /> </p>
<p align="center"> <strong>Agent-native short-drama production workstation.</strong> </p>
<p align="center"> Turn one story idea into a visible video canvas for minutes-long videos, powered by Seedance 2.0. </p>
<p align="center"> <a href="README.zh-CN.md"><strong>中文文档</strong></a> · <a href="https://seereel.studio/"><strong>Free web trial</strong></a> · <a href="https://seereel.studio/ai-use-me.html"><strong>AI use me</strong></a> · <a href="LICENSE">MIT License</a> </p>
<p align="center"> For everyday usage, the most cost-effective option is the CNY 200/month <a href="https://www.volcengine.com/docs/82379/2366394?lang=zh">Volcengine Agent Plan</a>. </p>
Requirements:
git clone https://github.com/feifeibear/seereel-agent.git
cd seereel-agent
npm install
cp .env.example .env
npm run dev
Open the printed local URL, usually:
http://localhost:5173
Production-style local run:
NODE_ENV=production PORT=5174 npm run start
Without provider keys, the app still opens and can be explored in mock mode. For real generation, configure API Keys and TOS.
Default route: Volcengine Agent Plan. One Agent Plan key can cover SeeReel's Seedream image generation, Seedance video generation, and Seed/VLM review path through the dedicated /api/plan/v3 route.
ARK_AGENT_PLAN_KEY=<your-agent-plan-key>
ARK_AGENT_PLAN_BASE=https://ark.cn-beijing.volces.com/api/plan/v3
SEEDREAM_AGENT_PLAN_MODEL=doubao-seedream-5.0-lite
SEEDANCE_AGENT_PLAN_MODEL=doubao-seedance-2-0-260128
SEEDANCE_AGENT_PLAN_FAST_MODEL=doubao-seedance-2-0-fast-260128
VISION_REVIEW_AGENT_PLAN_MODEL=doubao-seed-2.0-pro
VIDEO_ANALYZE_AGENT_PLAN_MODEL=doubao-seed-2.0-pro
Preferred local route when available: standard Ark API keys. If BP, CN, and Agent Plan keys are all configured, SeeReel uses BP > CN > Agent Plan:
BP_ARK_API_KEY=<your-standard-ark-api-key>
BP_SEEDREAM_API_KEY=<optional-seedream-only-bp-key>
BP_SEEDREAM_API_BASE=https://ark.ap-southeast.bytepluses.com/api/v3
BP_SEEDANCE_API_KEY=<optional-seedance-only-bp-key>
BP_SEEDANCE_API_BASE=https://ark.ap-southeast.bytepluses.com/api/v3
CN_ARK_API_KEY=<your-cn-ark-api-key>
CN_SEEDREAM_API_KEY=<optional-seedream-only-cn-key>
CN_SEEDREAM_API_BASE=https://ark.cn-beijing.volces.com/api/v3
CN_SEEDANCE_API_KEY=<optional-seedance-only-cn-key>
CN_SEEDANCE_API_BASE=https://ark.cn-beijing.volces.com/api/v3
SEEDANCE_CN_MODEL=doubao-seedance-2-0
TOS is separate and still required when local or Codex-generated references must be sent to remote Seedance workers:
TOS_ACCESS_KEY_ID=<AK>
TOS_SECRET_ACCESS_KEY=<SK>
TOS_REGION=cn-beijing
TOS_ENDPOINT=tos-cn-beijing.volces.com
TOS_BUCKET=<bucket>
TOS_KEY_PREFIX=cinema-agent/storyboards
TOS_PRESIGN_EXPIRES_SEC=604800
Volcengine doubao-music is a separate OpenAPI service for the post-stitch audio-track node. It does not use Ark /api/v3 or Agent Plan credentials:
VOLC_MUSIC_ACCESS_KEY_ID=<AK>
VOLC_MUSIC_SECRET_ACCESS_KEY=<SK>
VOLC_MUSIC_BILLING_MODE=postpaid
VOLC_MUSIC_MODEL_VERSION=v5.0
Fallback and optional providers:
| Capability | Environment |
|---|---|
| Seedream BP standard API | BP_ARK_API_KEY / BP_SEEDREAM_API_KEY |
| Seedream CN standard API | CN_ARK_API_KEY / CN_SEEDREAM_API_KEY |
| Seedance BP standard API | BP_ARK_API_KEY / BP_SEEDANCE_API_KEY |
| Seedance CN standard API | CN_ARK_API_KEY / CN_SEEDANCE_API_KEY |
| Agent Plan | ARK_AGENT_PLAN_KEY |
| Optional script generation | OPENAI_API_KEY / OAI_KEY |
| Optional narration | VOLC_TTS_APPID / VOLC_TTS_TOKEN |
| Optional music generation | VOLC_MUSIC_ACCESS_KEY_ID / VOLC_MUSIC_SECRET_ACCESS_KEY |
| Public media fallback | non-localhost PUBLIC_MEDIA_BASE_URL |
The public product currently runs at:
https://seereel.studio
For your own deployment, the simplest production shape is one Volcengine ECS instance with Caddy, persistent storage, and either Docker Compose or systemd. See deploy/volcengine.md for the full runbook.
Do not put a personal Agent Plan key into a public frontend bundle. For a public server:
seereelcli configure --agent-plan-token.This 30-second one-shot drone route was created from a single chat request and one reference image. SeeReel generated the final video while keeping the production graph visible: uploaded reference, storyboard nodes, Seedance shots, a tail-frame continuity bridge, and the stitch node.
User inputUser input
|
Codex reply (GPT 5.5)Done. The SeeReel session is:
Handoff link Final video preview: Canvas:
Validation result: 30.167s, 720x1280, 6.0 MB MP4 preview. SeeReel confirms that both shots are ready, stitch is ready, and there are 0 failed shots. The workflow keeps the uploaded reference image, two cloud storyboard segments, two 15s Seedance shots, shot 1's tail-frame asset Apart from uploading the user's local reference image and downloading the final video locally, all intermediate results were generated in the SeeReel cloud and kept in the session. |
The handoff link opens this session's workflow in the SeeReel web app.
The user does not only watch the final video. They can return to this canvas, revise the reference image, prompt, storyboard, generated shots, first-frame continuity bridge, or stitch node, and then continue production from the edited point.
Reference image source: 4K Wallpapers.
The web UI, CLI, and agents share the same API and persisted state.
| Task | Endpoint |
|---|---|
| Get full state | GET /api/state |
| Create session | POST /api/sessions |
| Generate script | POST /api/sessions/:sessionId/script/generate |
| Create / update assets | POST /api/assets, PATCH /api/assets/:assetId |
| Generate asset image | POST /api/assets/:assetId/generate |
| Generate storyboard | POST /api/sessions/:sessionId/storyboard |
| Publish storyboard references | POST /api/sessions/:sessionId/storyboards/publish-tos |
| Generate shot video | POST /api/shots/:shotId/generate |
| Poll shot video | POST /api/shots/:shotId/poll |
| Run shot review | POST /api/shots/:shotId/review |
| Stitch final video | POST /api/sessions/:sessionId/stitch |
| Poll stitch | POST /api/sessions/:sessionId/stitch/poll |
| Download final video | GET /api/sessions/:sessionId/download |
| Export editable session package | GET /api/sessions/:sessionId/export |
| Import editable session package | POST /api/sessions/import |
See AGENTS.md and .agents/skills/seereel-agent-session/reference.md for operating details.
SeeReel是一个易于使用的AI工作流工具,提供了一个易于使用的界面,允许用户创建和管理AI工作流。它适用于开发者和非开发者 alike.
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。
AI Skill Hub 点评:SeeReel 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | SeeReel |
| 原始描述 | 开源AI工作流:Agent-native Seedance 2.0 short-film studio: cli for AI, canvas for human。⭐9 · TypeScript |
| Topics | workflowagentclaude-codecodexseedance-2seedream-5typescript |
| GitHub | https://github.com/feifeibear/SeeReel |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-11 · 更新时间:2026-06-11 · 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