AI Templates

Ready-to-use project templates and boilerplates for building AI applications — Next.js AI templates, LangChain starters, and scaffolds for common AI patterns.

34 templates

7 categories

app-builders (17)mcp-servers (11)rag-knowledge (6)documentation (3)automation (2)deployment-infra (1)data-pipelines (1)

34 of 34

LlamaIndex StarterTemplate59/100Open Source

LlamaIndex starter pack for common RAG use cases.

12 capabilities·Ranked by quality 90, freshness 90

LangChain RAG TemplateTemplate59/100Open Source

LangChain reference RAG implementation from scratch.

14 capabilities·Ranked by quality 90, freshness 90

AI Dashboard TemplateTemplate59/100Open Source

AI-powered internal knowledge base dashboard template.

12 capabilities·Ranked by quality 90, freshness 90

LangChain TemplatesTemplate58/100Open Source

Official LangChain deployable application templates.

13 capabilities·Ranked by quality 90, freshness 90

create-t3-turboTemplate58/100Open Source

T3 stack monorepo with Next.js, Expo, tRPC, and Drizzle.

14 capabilities·Ranked by quality 90, freshness 90

AutoGen StarterTemplate58/100Open Source

Microsoft AutoGen multi-agent conversation samples.

14 capabilities·Ranked by quality 90, freshness 90

Vercel AI ChatbotTemplate57/100Open Source

Next.js AI chatbot template with Vercel AI SDK.

14 capabilities·Ranked by quality 90, freshness 90

SaaS AI StarterTemplate57/100Open Source

Open-source SaaS template with AI and payments built in.

14 capabilities·Ranked by quality 90, freshness 90

OpenAI Assistants TemplateTemplate57/100Open Source

OpenAI Assistants API quickstart with Next.js.

11 capabilities·Ranked by quality 90, freshness 90

Next.js AI TemplateTemplate57/100Open Source

Official Next.js starter for AI SDK integration.

13 capabilities·Ranked by quality 90, freshness 90

CrewAI TemplateTemplate57/100Open Source

CrewAI multi-agent collaboration example templates.

14 capabilities·Ranked by quality 90, freshness 90

ChatGPT Next WebTemplate57/100Open Source

One-click deployable ChatGPT web UI for all platforms.

14 capabilities·Ranked by quality 90, freshness 90

Horizon AI TemplateTemplate48/100Free

Create outstanding AI SaaS Apps & Prompts 10X...

14 capabilities·Ranked by freshness 90, quality 84

HeadshotGenerator.ioTemplate46/100Free

A Professional AI headshot generator starter kit powered by Next.js, Leap AI, and...

6 capabilities·Ranked by freshness 90, quality 77

llm-appTemplate43/100Open Source

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

14 capabilities·Ranked by freshness 90, ecosystem 70

ai-website-cloner-templateTemplate42/100Open Source

Clone any website with one command using AI coding agents

12 capabilities·Ranked by freshness 90, ecosystem 60

LogoFastTemplate34/100Free

Turbocharge Your Startup Launch with NextJS...

12 capabilities·Ranked by freshness 90, quality 52

AI SDLC Scaffold, repo template for AI-assisted software developmentTemplate34/100Open Source

I built an open-source repo template that brings structure to AI-assisted software development, starting from the pre-coding phases: objectives, user stories, requirements, architecture decisions.It's designed around Claude Code but the ideas are tool-agnostic. I've been a computer science

13 capabilities·Ranked by freshness 90, adoption 46

designing-real-world-ai-agents-workshopTemplate32/100Open Source

Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video

12 capabilities·Ranked by freshness 65, ecosystem 60

Smithery ScaffoldTemplate27/100Open Source

Provide a scaffold for building MCP servers with integrated AI and environment configuration support. Enable rapid development and deployment of MCP-compliant services using modern TypeScript tooling. Simplify the creation of MCP tools, resources, and prompts with built-in validation and runtime sup

3 capabilities·Ranked by freshness 90, quality 41

Smithery ScaffoldTemplate27/100Open Source

Provide a scaffold for building MCP servers with integrated schema validation and development tooling. Accelerate the creation of MCP-compliant servers by leveraging this scaffold's structure and dependencies. Simplify development with built-in support for the Model Context Protocol SDK and schema v

3 capabilities·Ranked by freshness 90, quality 41

TypeScript StarterTemplate27/100Open Source

Kickstart development with a customizable TypeScript template featuring sample tools for greeting, calculation, time, and image generation, plus an info resource. Adapt it to your needs by adding or modifying tools and resources. Get up and running fast with a clean project structure.

5 capabilities·Ranked by freshness 90, ecosystem 49

typescript-mcp-server-boilerplate-2Template26/100Open Source

Kickstart development with a ready-made TypeScript project for quickly adding tools, resources, and prompts. Customize sample actions like greeting, calculator, and image generation to fit your needs. Build and run immediately with minimal setup.

3 capabilities·Ranked by freshness 90, ecosystem 49

Next.js MCP Server TemplateTemplate26/100Open Source

** (Typescript) - A starter Next.js project that uses the MCP Adapter to allow MCP clients to connect and access resources.

10 capabilities·Ranked by freshness 90, quality 45

Smithery ScaffoldTemplate25/100Open Source

Provide a scaffold for building MCP servers with ease. Enable rapid development and testing of MCP tools and resources using a modern TypeScript setup. Simplify integration with the Model Context Protocol ecosystem.

4 capabilities·Ranked by freshness 90, ecosystem 39

Smithery ScaffoldTemplate25/100Open Source

3 capabilities·Ranked by freshness 90, ecosystem 39

Smithery ScaffoldTemplate24/100Open Source

Provide a scaffold for building MCP servers with ease. Enable rapid development and testing of MCP tools and resources using a modern TypeScript setup. Simplify MCP server creation with integrated SDK and schema validation.

3 capabilities·Ranked by freshness 90, ecosystem 39

Smithery ScaffoldTemplate24/100Open Source

Provide a flexible scaffold for building MCP servers with ease. Accelerate development by leveraging a ready-to-use framework that integrates MCP SDK and schema validation. Simplify creating and managing MCP tools, resources, and prompts in your applications.

3 capabilities·Ranked by freshness 90, ecosystem 39

Smithery ScaffoldTemplate24/100Open Source

Provide a scaffold for building MCP servers with tools and resources integration. Enable rapid development and testing of MCP capabilities using a modular and type-safe approach. Simplify the creation of MCP-compliant servers with built-in support for common patterns.

3 capabilities·Ranked by freshness 90, ecosystem 39

create-python-serverTemplate24/100Open Source

Create a Python MCP server

6 capabilities·Ranked by freshness 90, ecosystem 40

create-shieldedvaultTemplate23/100Open Source

Scaffold an AI agent with split-key custody, attestation, payments, and MCP tool discovery. ShieldedVault in 2 minutes.

4 capabilities·Ranked by freshness 90, ecosystem 50

astro-platform-starterTemplate21/100Open Source

MCP server: astro-platform-starter

3 capabilities·Ranked by freshness 90, ecosystem 49

vite-react-templateTemplate21/100Open Source

MCP server: vite-react-template

3 capabilities·Ranked by freshness 90, ecosystem 49

asma-genql-calendarTemplate20/100Open Source

autogen for calendar srv

5 capabilities·Ranked by freshness 90, ecosystem 30

Top Capabilities

Browse all →

code explanation and documentation generation10 artifacts

Analyzes selected code or entire files and generates natural language explanations of what the code does, how it works, and why certain patterns were chosen. The feature can produce documentation in multiple formats (docstrings, comments, markdown) and supports various documentation styles (JSDoc, Sphinx, etc.). Developers can request explanations at different levels of detail (high-level overview, line-by-line breakdown, architectural context) through the chat interface, with responses appearing as formatted text or code comments.

ChatGPT AIAI Pundit Magic - Design to Code | Figma to CodeCodeGPT: write and improve code using AI

context-aware code completion3 artifacts

Cody utilizes a context-aware engine that analyzes the current file and project structure to provide relevant code completions. It integrates with the Visual Studio Code API to access the Abstract Syntax Tree (AST) of the code, allowing it to suggest completions that are semantically relevant to the context, rather than relying solely on keyword matching. This approach ensures that the suggestions are not only syntactically correct but also contextually appropriate, enhancing developer productivity.

SupermavenCline 中文版Cody

natural-language-to-full-stack-application-generation2 artifacts

Converts natural language prompts into executable full-stack web applications by invoking an AI agent that generates React/Next.js frontend code, Node.js backend logic, and database schemas. The agent runs code in-browser via WebContainers to validate syntax and functionality before deployment, iterating on the generated code based on execution feedback. Token consumption scales with project complexity (larger codebases consume more tokens per iteration), and the agent supports design system imports from Figma and GitHub to accelerate UI generation.

LovableBolt.new

model size selection with speed-accuracy tradeoffs across 6 variants2 artifacts

Provides six model variants (tiny, base, small, medium, large, turbo) with parameter counts ranging from 39M to 1550M, enabling developers to choose optimal speed-accuracy tradeoffs. Tiny model runs at ~10x speed with 1GB VRAM; large model runs at 1x speed with 10GB VRAM. English-only variants (tiny.en, base.en, small.en) provide higher English accuracy by removing multilingual capacity. Turbo model (809M params) offers 8x speedup over large with minimal accuracy loss but lacks translation support.

WhisperWhisper CLI

direct speech-to-english translation without intermediate transcription2 artifacts

Translates non-English speech directly to English text by using a task-specific token in the TextDecoder that signals translation mode, bypassing the need for intermediate transcription-then-translation pipelines. The AudioEncoder processes mel spectrograms identically to transcription, but the decoder generates English tokens directly from audio embeddings, reducing latency and error propagation compared to cascaded systems.

WhisperWhisper CLI

multilingual speech-to-text transcription with language-agnostic encoder2 artifacts

Transcribes audio in 98 languages to text in the original language using a unified Transformer sequence-to-sequence architecture with a shared AudioEncoder that processes mel spectrograms into language-agnostic embeddings, then a TextDecoder that generates tokens autoregressively. The system handles variable-length audio by padding or trimming to 30-second segments and uses task-specific tokens to signal transcription mode, enabling a single model to handle multiple languages without language-specific branches.

WhisperWhisper CLI

automatic language identification from audio with 98-language support2 artifacts

Detects the spoken language in audio by processing mel spectrograms through the AudioEncoder and using a language classification head that outputs probability distributions over 98 supported languages. The model leverages 680K hours of multilingual training data to recognize language characteristics from acoustic features alone, without requiring transcription. Language detection occurs as a preliminary step in the transcription pipeline and can be called independently via the language detection task token.

Whisper Large v3Whisper CLI

self-hosted-deployment-with-docker2 artifacts

W&B Personal tier (free) and Enterprise tier support self-hosted deployment via Docker, enabling on-premise installation for teams with data residency or security requirements. Self-hosted instances run independently from W&B cloud, with optional integration to W&B cloud for cross-instance features. Supports custom domain configuration, HTTPS, and integration with corporate identity providers (LDAP, SAML, OAuth).

Weights & BiasesWeights & Biases API

Browse Other Types

Agents

Autonomous AI systems that act on your behalf

Models

Foundation models, fine-tunes, and specialized AI models

MCP Servers

Model Context Protocol tools and integrations

Repositories

Open-source AI projects on GitHub

APIs

Programmatic endpoints for AI capabilities

Extensions

Browser and IDE extensions powered by AI

View all 19 types →

Search the match graph →Submit an artifact