能力标签

🤖 Agent 🔄 工作流 👁 OCR 🌐 翻译 🐳 Docker 💻 CLI 🔗 REST API 🧬 Embedding 📚 RAG 🖼 视觉

⚙️

Agent工作流

全栈AI代理模板

基于 Python · 无代码搭建完整 AI 自动化流程

英文名：full-stack-ai-agent-template

⭐ 1.3k Stars 🍴 261 Forks 💻 Python 📄 MIT 🏷 AI 8.0分

8.0AI 综合评分

AI代理模板FastAPINext.js

⬇ 下载源码 ZIP ⚙️ 配置说明

✦ AI Skill Hub 推荐

AI Skill Hub 强烈推荐：全栈AI代理模板是一款优质的Agent工作流。已获得 1.3k 颗 GitHub Star，AI 综合评分 8.0 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。

📚 深度解析

全栈AI代理模板是一套完整的 AI Agent 自动化工作流方案。随着 AI 能力的不断提升，基于 Agent 的自动化工作流正在成为提升个人和团队效率的核心方式。区别于传统的 RPA 自动化（模拟鼠标键盘操作），AI Agent 工作流通过理解任务意图、动态规划执行路径，能够处理更复杂的非结构化任务。

全栈AI代理模板工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。

在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 8.0 分，是同类 Agent 工作流中的精选推荐。

📋 工具概览

快速生成AI应用，集成FastAPI和Next.js

全栈AI代理模板是一套完整的 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。

GitHub Stars

⭐ 1.3k

开发语言

Python

支持平台

Windows / macOS / Linux

维护状态

正常维护，社区驱动

开源协议

MIT

AI 综合评分

8.0 分

工具类型

Agent工作流

Forks

261

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

快速生成AI应用，集成FastAPI和Next.js

📌 核心特色

可视化 Agent 工作流编排，无需编写复杂代码
支持多步骤自动化任务链，实现全流程无人值守
与外部 API、数据库和第三方服务无缝集成
内置错误处理与自动重试机制，保障稳定运行
提供可复用的自动化模板，快速在同类场景部署

🎯 主要使用场景

自动化日常重复性工作，将精力集中于创造性任务
构建数据采集 → 处理 → 输出的完整自动化管线
实现跨平台、跨系统的数据流转和业务协同

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 方式一：pip 安装（推荐）
pip install full-stack-ai-agent-template

# 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 full-stack-ai-agent-template

# 方式三：从源码安装（获取最新功能）
git clone https://github.com/vstorm-co/full-stack-ai-agent-template
cd full-stack-ai-agent-template
pip install -e .

# 验证安装
python -c "import full_stack_ai_agent_template; print('安装成功')"

📋 安装步骤说明

访问 GitHub 仓库获取工作流文件
在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
上传工作流文件
按照提示配置必要的环境变量和 API Key
运行测试确认流程正常后投入使用

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 命令行使用
full-stack-ai-agent-template --help

# 基本用法
full-stack-ai-agent-template input_file -o output_file

# Python 代码中调用
import full_stack_ai_agent_template

# 示例
result = full_stack_ai_agent_template.process("input")
print(result)

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

# full-stack-ai-agent-template 配置文件示例（config.yml）
app:
  name: "full-stack-ai-agent-template"
  debug: false
  log_level: "INFO"

# 运行时指定配置文件
full-stack-ai-agent-template --config config.yml

# 或通过环境变量配置
export FULL_STACK_AI_AGENT_TEMPLATE_API_KEY="your-key"
export FULL_STACK_AI_AGENT_TEMPLATE_OUTPUT_DIR="./output"

📑 README 深度解析真实文档完整度 94/100 含工作流图查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

Full-Stack AI Agent Template

Production-ready FastAPI + Next.js project generator with AI agents, RAG, and 20+ enterprise integrations.

<a href="#-quick-start">Quick Start</a> • <a href="#-features">Features</a> • <a href="#-demo">Demo</a> • <a href="https://vstorm-co.github.io/full-stack-ai-agent-template/">Documentation</a> • <a href="https://oss.vstorm.co/projects/full-stack-ai-agent-template/configurator/">Configurator</a> • <a href="https://pypi.org/project/fastapi-fullstack/">PyPI</a>

🤖 6 AI Agent Frameworks (PydanticAI, PydanticDeep, LangChain, LangGraph, CrewAI, DeepAgents) 📄 RAG Pipeline (Milvus, Qdrant, pgvector, ChromaDB) ⚡ FastAPI + Next.js 15 (WebSocket streaming, real-time chat UI) 🔗 Conversation Sharing (direct sharing, public links, admin browser) 🔒 Enterprise-Ready (JWT, OAuth, admin panel, Celery, Docker, K8s)

<details> <summary>Table of Contents</summary>

Quick Start
Demo
Screenshots
Why This Template
Features
Architecture
AI Agent
RAG
Observability
Django-style CLI
Generated Project Structure
Configuration Options
Comparison
FAQ
Documentation
Contributing

</details>

---

🗺️ Architecture Overview

┌──────────────────────────────────────────────────────────────────────────┐
│                         FRONTEND  (Next.js 15)                           │
│  Chat UI · Knowledge Base · Dashboard · Settings · Dark Mode · i18n      │
└──────────────┬───────────────────────────────────────────┬───────────────┘
               │  REST / WebSocket                         │  Vercel
               ▼                                           ▼
┌──────────────────────────────────────────────────────────────────────────┐
│                         BACKEND  (FastAPI)                               │
│                                                                          │
│  ┌─────────────────────────────────────────────────────────────────┐     │
│  │                     AI AGENTS                                   │     │
│  │  PydanticAI · LangChain · LangGraph · CrewAI · DeepAgents       │     │
│  │  ────────────────────────────────────────────────────────────   │     │
│  │  Tools: datetime · web_search (Tavily) · search_knowledge_base  │     │
│  │  Providers: OpenAI · Anthropic · Gemini · OpenRouter            │     │
│  └─────────────────────────────────────────────────────────────────┘     │
│                                                                          │
│  ┌─────────────────────────────────────────────────────────────────┐     │
│  │                     RAG PIPELINE                                │     │
│  │                                                                 │     │
│  │  Sources        Parse           Chunk          Embed            │     │
│  │  ─────────      ──────────      ──────────     ──────────────   │     │
│  │  Local files    PyMuPDF         recursive      OpenAI           │     │
│  │  API upload     LiteParse       markdown       Voyage           │     │
│  │  Google Drive   LlamaParse      fixed          Gemini (multi)   │     │
│  │  S3/MinIO       python-docx                    SentenceTransf.  │     │
│  │  Sync Sources                                                   │     │
│  │                                                                 │     │
│  │  Store              Search              Rank                    │     │
│  │  ──────────────     ──────────────      ──────────────          │     │
│  │  Milvus             Vector similarity   Cohere reranker         │     │
│  │  Qdrant             BM25 + vector RRF   CrossEncoder            │     │
│  │  ChromaDB           Multi-collection                            │     │
│  │  pgvector                                                       │     │
│  └─────────────────────────────────────────────────────────────────┘     │
│                                                                          │
│  Auth (JWT/API Key/OAuth) · Rate Limiting · Webhooks · Admin Panel       │
│  Background Tasks (Celery/Taskiq/ARQ) · Django-style CLI                 │
│  Observability (Logfire/LangSmith/Sentry/Prometheus)                     │
└───────┬──────────────┬──────────────┬──────────────┬─────────────────────┘
        │              │              │              │
        ▼              ▼              ▼              ▼
   PostgreSQL       Redis         Vector DB      LLM APIs
   MongoDB                        (Milvus/       (OpenAI/
   SQLite                         Qdrant/        Anthropic/
                                  ChromaDB/      Gemini)
                                  pgvector)

---

✨ Features

Features

Document parsing - PDF (PyMuPDF with tables, headers/footers, OCR), DOCX, TXT, MD + 130+ formats via LlamaParse
Image description - Extract images from documents, describe via LLM vision API (opt-in)
Chunking - RecursiveCharacterTextSplitter with configurable size/overlap
Reranking - Cohere API or local CrossEncoder for improved search quality
Agent integration - All 6 AI frameworks get a search_knowledge_base tool automatically

---

Installation

```bash

Use presets for common setups

fastapi-fullstack create my_ai_app --preset production # Full production setup fastapi-fullstack create my_ai_app --preset ai-agent # AI agent with streaming

4. Build WebSocket streaming for AI responses

8. Build Next.js frontend with auth and chat UI

9. Write Docker Compose for all services

🚀 Quick Start

[!TIP] Prefer a visual configurator? Use the Web Configurator to configure your project in the browser and download a ZIP — no CLI installation needed.

Usage

```python

🎬 Demo

CLI generator:

File upload & RAG ingestion:

---

📸 Screenshots

Quick mode with options

fastapi-fullstack create my_ai_app \ --database postgresql \ --frontend nextjs

Environments

`make` target	Compose file	When to use
`make dev`	`docker-compose.dev.yml`	Local development with hot-reload + bind-mounted source.
`make stage`	`docker-compose.yml`	Production-like build (no bind mounts) running on localhost. Sanity-check before deploy.
`make prod`	`docker-compose.prod.yml`	Production. Requires `backend/.env` (copy from `backend/.env.example`, fill real secrets) + external Nginx using `nginx/nginx.conf`.

Each env has matching -down, -logs, -rebuild siblings.

[!NOTE] Windows users: make requires GNU Make. Install via Chocolatey (choco install make) or use WSL2 / Git Bash. The Docker workflow is identical across macOS, Linux, and WSL2.

<details> <summary>Local backend (no Docker, for IDE breakpoints)</summary>

If you want to run the backend on the host while the database stays in Docker:

```bash cd my_ai_app make install # uv sync + pre-commit hooks

Configure your nginx host using nginx/nginx.conf as reference

make prod # builds + starts + migrates make prod-logs # tail logs


For frontend deployment to **Vercel**:

bash cd frontend && npx vercel --prod ```

In the Vercel dashboard set BACKEND_URL, BACKEND_WS_URL, NEXT_PUBLIC_AUTH_ENABLED=true.

</details>

Profile & Settings

Profile — Personal info tab: avatar upload, display name, email, and active session list with per-device revoke buttons. Visibility note explains which fields are shown to teammates.

Account & Security — Change password form with strength guidance, "Sign out everywhere" button, and danger zone for permanent account deletion.

Slash Commands — Customize the /command palette in chat. Toggle built-in commands (/clear, /regen, /settings, /summarize, /explain) and create custom shortcuts that send a stored prompt with a few keystrokes.

Appearance — Theme switcher (light / dark / system) and brand color picker with four presets: Blue (Stripe/Vercel), Green (healthtech), Red (energetic), Orange (B2C), Violet (Anthropic-style). Brand color updates CSS variables across the entire workspace and is saved per-device.

Notification Preferences — Per-category notification controls with separate toggles for email and in-app delivery. Categories: Billing, Team activity, Security alerts, and Product updates. Preferences stored locally and synced to the backend via /users/me/notifications.

.env

LANGCHAIN_TRACING_V2=true LANGCHAIN_API_KEY=your-api-key LANGCHAIN_PROJECT=my_project ```

Configuration

Enable Logfire and select which components to instrument:

```bash fastapi-fullstack new

⚙️ Configuration Options

Core Options

Option	Values	Description
Database	`postgresql`, `mongodb`, `sqlite`, `none`	Async by default
ORM	`sqlalchemy`, `sqlmodel`	SQLModel for simplified syntax
Auth	`jwt`, `api_key`, `both`, `none`	JWT includes user management
OAuth	`none`, `google`	Social login
AI Framework	`pydantic_ai`, `langchain`, `langgraph`, `crewai`, `deepagents`	Choose your AI agent framework
LLM Provider	`openai`, `anthropic`, `google`, `openrouter`	OpenRouter only with PydanticAI
RAG	`--rag`	Enable RAG with vector database
Vector Store	`milvus`, `qdrant`, `chromadb`, `pgvector`	pgvector uses existing PostgreSQL
Background Tasks	`none`, `celery`, `taskiq`, `arq`	Distributed queues
Frontend	`none`, `nextjs`	Next.js 15 + React 19

2. Configure SQLAlchemy + Alembic migrations

7. Configure Celery + Redis for background tasks

Done. All of the above, configured and working.

```

The CLI command is: uv run <project_slug> <command>

uv run my_ai_app server run --reload # Start dev server uv run my_ai_app db migrate -m "message" # Create migration uv run my_ai_app db upgrade # Apply migrations uv run my_ai_app user create-admin # Create admin user ```

Use make help to see all available Makefile shortcuts.

---

Monitoring & API

Celery Flower — Real-time task queue monitor. Track worker status, task throughput, and failure rates for background jobs (document ingestion, email, webhooks).

Flower

API Documentation — Auto-generated OpenAPI / Swagger UI at /docs. All endpoints documented with request/response schemas, auth requirements, and example payloads.

API Docs

---

⚡ Backend (FastAPI)

FastAPI + Pydantic v2 - High-performance async API
Multiple Databases - PostgreSQL (async), MongoDB (async), SQLite
Authentication - JWT + Refresh tokens, API Keys, OAuth2 (Google)
Background Tasks - Celery, Taskiq, or ARQ
Django-style CLI - Custom management commands with auto-discovery

✓ Instrument FastAPI

✓ Rate limiting (slowapi)

✓ Pagination (fastapi-pagination)

1. Set up FastAPI project structure

🔌 20+ Enterprise Integrations

Category	Integrations
AI Frameworks	PydanticAI, PydanticDeep, LangChain, LangGraph, CrewAI, DeepAgents
LLM Providers	OpenAI, Anthropic, Google Gemini, OpenRouter
RAG / Vector Stores	Milvus, Qdrant, ChromaDB, pgvector
RAG Sources	Local files, API upload, Google Drive, S3/MinIO, Sync Sources (configurable, scheduled)
Embeddings	OpenAI, Voyage, Gemini (multimodal), SentenceTransformers
Caching & State	Redis, fastapi-cache2
Security	Rate limiting, CORS, CSRF protection
Observability	Logfire, LangSmith, Sentry, Prometheus
Admin	SQLAdmin panel with auth
Collaboration	Conversation sharing (direct + link), admin conversation browser
Messaging	Telegram multi-bot (polling + webhook), Slack multi-bot (Events API + Socket Mode)
Events	Webhooks, WebSockets
DevOps	Docker, GitHub Actions, GitLab CI, Kubernetes

PydanticAI Integration

Type-safe agents with full dependency injection:

```python

LangChain Integration

Flexible agents with LangGraph:

```python

Integrations

Select what you need:

```bash fastapi-fullstack new

6. Set up RAG pipeline (parsing, chunking, embedding, vector store)

🔄 Comparison

vs. Manual Setup

Setting up a production AI agent stack manually means wiring together 10+ tools yourself:

```bash

vs. Alternatives

Feature	This Template	[full-stack-fastapi-template](https://github.com/fastapi/full-stack-fastapi-template)	[create-t3-app](https://github.com/t3-oss/create-t3-app)
AI Agents (5 frameworks)	✅	❌	❌
RAG Pipeline (4 vector stores)	✅	❌	❌
WebSocket Streaming	✅	❌	❌
Conversation Persistence	✅	❌	❌
LLM Observability (Logfire/LangSmith)	✅	❌	❌
FastAPI Backend	✅	✅	❌
Next.js Frontend	✅ (v15)	❌	✅
JWT + OAuth Authentication	✅	✅	✅ (NextAuth)
Background Tasks (Celery/Taskiq/ARQ)	✅	✅ (Celery)	❌
Admin Panel	✅ (SQLAdmin)	❌	❌
Multiple Databases (PG/Mongo/SQLite)	✅	PostgreSQL only	Prisma
Docker + K8s	✅	✅	❌
Interactive CLI Wizard	✅	❌	✅
Django-style Commands	✅	❌	❌
Document Sources (GDrive, S3, API)	✅	❌	❌
AI-Agent Friendly (CLAUDE.md)	✅	❌	❌

---

❓ FAQ

<details> <summary>How is this different from full-stack-fastapi-template?</summary>

full-stack-fastapi-template by @tiangolo is a great starting point for FastAPI projects, but it focuses on traditional web apps. This template is purpose-built for AI/LLM applications — it adds AI agents (5 frameworks), RAG with 4 vector stores, WebSocket streaming, conversation persistence, LLM observability, and a Next.js chat UI out of the box.

</details>

<details> <summary>Can I use this without AI/LLM features?</summary>

Yes. The AI agent and RAG modules are optional. You can use this as a pure FastAPI + Next.js template with auth, admin panel, background tasks, and all other infrastructure — just skip the AI framework selection during setup.

</details>

<details> <summary>What Python and Node.js versions are required?</summary>

Python 3.11+ and Node.js 18+ (for the Next.js frontend). We recommend using uv for Python and bun for the frontend.

</details>

<details> <summary>Can I add integrations after project generation?</summary>

The generated project is plain code — no lock-in or runtime dependency on the generator. You can add, remove, or modify any integration manually. The template just gives you a well-structured starting point.

</details>

<details> <summary>Can I use a different LLM provider than the one I selected?</summary>

Yes. The LLM provider is configured via environment variables (AI_MODEL, OPENAI_API_KEY, etc.). You can switch providers by changing the .env file and the model name — no code changes needed for PydanticAI (which supports all providers natively).

</details>

---

🎯 aiskill88 AI 点评 A 级 2026-05-27

高质量的全栈AI代理模板，易于使用

⚡ 核心功能

可视化 Agent 工作流编排，无需编写复杂代码
支持多步骤自动化任务链，实现全流程无人值守
与外部 API、数据库和第三方服务无缝集成
内置错误处理与自动重试机制，保障稳定运行
提供可复用的自动化模板，快速在同类场景部署

👥 适合人群

自动化工程师和运维人员项目经理和业务分析师希望减少重复性工作的专业人士数字化转型团队

🎯 使用场景

自动化日常重复性工作，将精力集中于创造性任务
构建数据采集 → 处理 → 输出的完整自动化管线
实现跨平台、跨系统的数据流转和业务协同

⚖️ 优点与不足

✅ 优点

+MIT 协议，可免费商用
+大幅减少重复性人工操作
+可视化流程，清晰直观
+可扩展性强，支持复杂场景

⚠️ 不足

−初始配置和调试需投入一定时间
−强依赖外部服务的稳定性
−复杂场景需具备一定技术基础

⚠️ 使用须知

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。

📄 License 说明

🔗 相关工具推荐

LangChain AI开发框架

Agent工作流

ai-agents-for-beginners Agent工作流

微软官方开源项目，提供12堂系统课程学习AI智能体框架。涵盖工作流设计、RAG检索增强、多智能体协作等核心技能。适合AI

🧩 你可能还需要

基于当前 Skill 的能力图谱，自动补全的工具组合

❓ 常见问题 FAQ

如何使用该模板?−

参考README文档，按照步骤安装和运行

什么是 Agent 工作流？和普通自动化有什么区别？+

导入工作流后，我需要修改哪些配置？+

工作流运行失败了，如何排查问题？+

这个工作流每次运行会产生哪些费用？+

工作流可以定时自动运行吗？+

💡 AI Skill Hub 点评

总体来看，全栈AI代理模板是一款质量优秀的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。

⬇️ 获取与下载

⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习全栈AI代理模板

查看分步骤安装教程和完整使用指南，快速上手这款工具

⚙️ 安装教程 📚 使用教程

🌐 原始信息

原始名称	`full-stack-ai-agent-template`
Topics	`AI代理模板FastAPINext.js`
GitHub	https://github.com/vstorm-co/full-stack-ai-agent-template
License	MIT
语言	Python

🔗 原始来源

🐙 GitHub 仓库 https://github.com/vstorm-co/full-stack-ai-agent-template 🌐 官方网站 https://vstorm-co.github.io/full-stack-ai-agent-template/

收录时间：2026-05-27 · 更新时间：2026-05-27 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。

全栈AI代理模板

简介

Full-Stack AI Agent Template

🗺️ Architecture Overview

✨ Features

Features

Installation

Use presets for common setups

4. Build WebSocket streaming for AI responses

8. Build Next.js frontend with auth and chat UI

9. Write Docker Compose for all services

🚀 Quick Start

Usage

🎬 Demo

📸 Screenshots

Quick mode with options

Environments

Configure your nginx host using nginx/nginx.conf as reference

Profile & Settings

.env

Configuration

⚙️ Configuration Options

Core Options

2. Configure SQLAlchemy + Alembic migrations

7. Configure Celery + Redis for background tasks

Done. All of the above, configured and working.

The CLI command is: uv run <project_slug> <command>

Monitoring & API

⚡ Backend (FastAPI)

✓ Instrument FastAPI

✓ Rate limiting (slowapi)

✓ Pagination (fastapi-pagination)

1. Set up FastAPI project structure

🔌 20+ Enterprise Integrations

PydanticAI Integration

LangChain Integration

Integrations

6. Set up RAG pipeline (parsing, chunking, embedding, vector store)

🔄 Comparison

vs. Manual Setup

vs. Alternatives

❓ FAQ

🤖 交给 Agent 安装 · 全栈AI代理模板