AI agents marketplace for AI engineers: Discover specialized digital assistants from your trusted AI automation agency. Transform workflows today.

AI Agents for AI engineers | AI Agent Store

Vapi is a comprehensive platform designed for developers to efficiently build, test, and deploy AI-driven voice agents. It offers flexible APIs that facilitate the creation of custom conversational flows and integration with existing systems such as customer relationship management (CRM) and electronic health records (EHR). Vapi's low-latency architecture ensures real-time, natural interactions, making it ideal for applications in customer support, sales outreach, and more. The platform is engineered to handle millions of concurrent calls, leveraging a Kubernetes-based infrastructure to provide scalable and reliable voice AI solutions.

Vapi

vapi

A developer-centric platform enabling rapid creation, testing, and deployment of AI-powered voice agents for seamless integration into various applications.

Vercel AI SDK is a free, open-source TypeScript library from the creators of Next.js, designed to help developers build AI-powered applications and agents. It offers a unified provider API—OpenAI, Anthropic, Claude, Google Gemini, etc.—structured output (via Zod), streaming responses, chat UI integrations, tool calling, agentic loops, and full TypeScript type safety across React, Svelte, Vue, Angular, or Node apps. With over 2 million weekly downloads, it simplifies LLM integration and enables rapid development of robust AI workflows.

Vercel AI SDK

vercel-ai-sdk

Free open-source TypeScript SDK for building LLM-powered apps and agents across frameworks with unified API.

Amazon Bedrock AgentCore is a modular suite of AWS services providing secure, scalable deployment and operations for AI agents. It offers Runtime for serverless agent execution with session isolation and long-running support, Memory for context-aware agents, Identity for secure access, Gateway to convert APIs into agent-ready tools, Browser for managed web automation, Code Interpreter for sandboxed code execution, and Observability for tracing and debugging workflows. AgentCore supports any open-source framework and any foundation model, inside or outside Bedrock, enabling developers to accelerate agents into production with enterprise-grade flexibility, security, and monitoring.

Amazon Bedrock AgentCore

amazon-bedrock-agentcore

Modular AWS platform for deploying, enhancing, and monitoring AI agents securely at scale.

Kiro is an agentic Integrated Development Environment from AWS that transforms user prompts into structured specs, designs, and tasks. It integrates multimodal input, agent hooks for automation, MCP tool access, real-time code diffs, and supports local/cloud execution to help developers move from prototype to production.

Kiro AI IDE

kiro-ai-ide

Agentic AI IDE by AWS for spec-driven coding, multimodal chat, and automated agent hooks.

AgentScope is an open‑source, developer‑centric multi‑agent platform for building, orchestrating, and deploying LLM‑powered agent systems. It features explicit message passing, zero‑code drag‑and‑drop UI, built‑in tool and MCP support, distributed execution, monitoring, automatic prompt tuning, and fault tolerance.

AgentScope

agentscope

Open‑source multi‑agent framework with drag‑and‑drop UI, distributed execution, tool calls, and fault tolerance.

Strands Agents is an open‑source SDK from AWS for building production‑ready AI agents using a model‑driven architecture. It supports any LLM provider, rich tool integration (including MCP and AWS services), multi‑agent workflows, observability via OpenTelemetry, and deployment in local or cloud environments.

Strands Agents

strands-agents

Open‑source SDK for building and orchestrating single or multi‑agent systems with LLMs and tool integration.

MCP‑Use is an open‑source library and platform that lets developers connect any LangChain‑compatible LLM to Model Context Protocol (MCP) servers. It enables creation of AI agents with tool access—like browsing, file operations, or HTTP services—supporting multi‑server setups, dynamic tool selection, streaming output, and both hosted and self‑hosted deployment options.

MCP‑Use

mcp-use

Open‑source platform to connect LLMs with MCP servers and build custom AI agents with tool access.

markdown2pdf.ai offers a pay-per-call API, SDKs (Python, TypeScript, MCP), and a REST endpoint that convert Markdown to print‑ready PDFs using LaTeX. Payments are handled via Lightning Network (≈5 sats per PDF), no signup required.

markdown2pdf.ai

markdown2pdf-ai

API and SDKs that convert Markdown to high‑quality PDFs via Lightning payments.

AgentAuth is a developer-focused authentication layer designed to empower AI agents with secure, seamless access to over 250 popular applications. Tailored for AI agents, it simplifies the complexities of authentication by supporting OAuth 2.0, API keys, JWT, and more. With built-in support for leading agentic frameworks like LangChain, CrewAI, and LlamaIndex, AgentAuth ensures that AI agents can interact with tools such as Gmail, Slack, Salesforce, and Google Calendar without manual integration overhead. Its unified dashboard offers complete visibility into user-connected accounts, facilitating efficient monitoring and issue resolution. By handling the intricacies of authentication, AgentAuth allows developers to focus on building innovative, user-centric AI solutions.

AgentAuth

agentauth

Authentication layer enabling AI agents to securely access 250+ apps on users' behalf.

Dcup is an open-source, self-hostable Retrieval-Augmented Generation (RAG) platform designed to help developers and teams build scalable, AI-powered retrieval pipelines. It enables seamless integration with data sources like Google Drive, Dropbox, and AWS, and supports advanced search capabilities including LLM re-ranking, summary indexing, and hybrid search using OpenAI embeddings and Qdrant vector storage. With its intuitive Retrieval API and modular architecture, Dcup simplifies the process of ingesting, indexing, and retrieving data, making it ideal for AI applications requiring efficient and accurate information retrieval.

Dcup

dcup

An open-source RAG-as-a-Service platform for building scalable, AI-powered retrieval pipelines.

Natoma MCP Platform is a hosted solution that simplifies the integration of AI agents with enterprise tools and data sources using the Model Context Protocol (MCP). It offers one-click deployment of over 100 prebuilt MCP servers, enabling secure and scalable connections between large language models and various applications. The platform provides features like fine-grained authorization, secure data handling, and comprehensive audit logs, facilitating the adoption of agentic AI in enterprise environments.

Natoma MCP Platform

natoma-mcp-platform

A hosted platform for integrating AI agents with tools and data via managed Model Context Protocol servers.

Awesome MCP Servers is a GitHub-curated list compiling various MCP (Model Context Protocol) servers that allow large language models to interface with external tools, files, APIs, databases, and more. These servers empower AI agents to perform tasks beyond simple text generation by enabling them to access structured resources and execute contextual operations. The list features both production-ready and experimental implementations contributed by the community.

Awesome MCP Servers

awesome-mcp-servers

A curated list of Model Context Protocol (MCP) servers enhancing AI capabilities with external tools and data.