# Agent Stack Directory

> A checked directory of 54 infrastructure tools for AI agents across 11 categories. Updated daily. Free to browse. Paid placements are labeled and never change organic order.

## New this week
- [Agent 37](https://agentstackdirectory.com/tools/agent-37/): Cloud sandboxes for running AI agents, positioned as lower-cost agent infrastructure. Official site: https://www.agent37.com/
- [Pickle Browser](https://agentstackdirectory.com/tools/pickle-browser/): Local browser that opens real pages for agents, shows its work on your machine, and needs no account. Official site: https://picklebrowser.com/
- [AIO Sandbox](https://agentstackdirectory.com/tools/aio-sandbox/): All-in-one agent sandbox with browser, shell, file access, VSCode Server, and MCP in one container. Official site: https://sandbox.agent-infra.com/
- [Browserbase](https://agentstackdirectory.com/tools/browserbase/): Hosted headless browsers for agents, with session control and an MCP server. Official site: https://www.browserbase.com/
- [Browser Use](https://agentstackdirectory.com/tools/browser-use/): Open-source browser agent library plus hosted remote browsers for AI agents. Official site: https://browser-use.com/
- [Steel](https://agentstackdirectory.com/tools/steel/): Open-source browser API for running fleets of cloud browsers for agents. Official site: https://steel.dev/
- [Hyperbrowser](https://agentstackdirectory.com/tools/hyperbrowser/): Cloud Chrome sessions, isolated sandboxes, and web data APIs for agents. Official site: https://www.hyperbrowser.ai/
- [Stagehand](https://agentstackdirectory.com/tools/stagehand/): SDK for browser agents with a Playwright-style API and self-healing selectors. Official site: https://www.stagehand.dev/

## Categories
- [Browsers & Computer Use](https://agentstackdirectory.com/category/browsers/): Cloud browsers and SDKs that let agents use the web. 8 tools.
- [Code Sandboxes](https://agentstackdirectory.com/category/sandboxes/): Isolated machines where agents can safely run code. 8 tools.
- [Memory & Context](https://agentstackdirectory.com/category/memory/): Long-term memory layers so agents remember users and tasks. 5 tools.
- [Search & Web Data](https://agentstackdirectory.com/category/search/): APIs that give agents fresh web search and clean page content. 7 tools.
- [Email](https://agentstackdirectory.com/category/email/): Inboxes and sending APIs for agents that talk over email. 3 tools.
- [Integrations & Auth Tools](https://agentstackdirectory.com/category/integrations/): Prebuilt tool calls and managed OAuth for thousands of apps. 5 tools.
- [Payments](https://agentstackdirectory.com/category/payments/): Ways for agents to charge, pay, and hold credentials. 3 tools.
- [Voice Agents](https://agentstackdirectory.com/category/voice/): Platforms for phone and voice agents. 3 tools.
- [Observability & Evals](https://agentstackdirectory.com/category/observability/): Tracing, debugging, and evals for agents in production. 5 tools.
- [Agent Frameworks](https://agentstackdirectory.com/category/frameworks/): Libraries for building agents and multi-agent workflows. 6 tools.
- [Identity](https://agentstackdirectory.com/category/auth/): Login, permissions, and token handling for agents. 1 tool.

## Tools
- [Browserbase](https://agentstackdirectory.com/tools/browserbase/): Hosted headless browsers for agents, with session control and an MCP server. Official site: https://www.browserbase.com/
- [Browser Use](https://agentstackdirectory.com/tools/browser-use/): Open-source browser agent library plus hosted remote browsers for AI agents. Official site: https://browser-use.com/
- [Steel](https://agentstackdirectory.com/tools/steel/): Open-source browser API for running fleets of cloud browsers for agents. Official site: https://steel.dev/
- [Hyperbrowser](https://agentstackdirectory.com/tools/hyperbrowser/): Cloud Chrome sessions, isolated sandboxes, and web data APIs for agents. Official site: https://www.hyperbrowser.ai/
- [Stagehand](https://agentstackdirectory.com/tools/stagehand/): SDK for browser agents with a Playwright-style API and self-healing selectors. Official site: https://www.stagehand.dev/
- [Anchor Browser](https://agentstackdirectory.com/tools/anchor-browser/): Infrastructure for computer-use agents that automate web tasks at scale. Official site: https://anchorbrowser.io/
- [Kernel](https://agentstackdirectory.com/tools/kernel/): Browser infrastructure for web agents with reusable sessions and fast spin-up. Official site: https://www.kernel.sh/
- [E2B](https://agentstackdirectory.com/tools/e2b/): Isolated cloud machines for agents to run code, browse, and use tools. Official site: https://e2b.dev/
- [Daytona](https://agentstackdirectory.com/tools/daytona/): Secure sandboxes for running AI-generated code. Official site: https://www.daytona.io/
- [Modal](https://agentstackdirectory.com/tools/modal/): Serverless cloud for running, training, and serving AI workloads, including sandboxes. Official site: https://modal.com/
- [Vercel Sandbox](https://agentstackdirectory.com/tools/vercel-sandbox/): Isolated Linux microVMs on Vercel for untrusted or agent-generated code. Official site: https://vercel.com/docs/sandbox
- [Runloop](https://agentstackdirectory.com/tools/runloop/): Code sandboxes (Devboxes) for AI coding agents, plus evaluations. Official site: https://runloop.ai/
- [Cloudflare Sandbox SDK](https://agentstackdirectory.com/tools/cloudflare-sandbox-sdk/): Run untrusted or generated code in Linux VMs or isolated Workers on Cloudflare. Official site: https://developers.cloudflare.com/sandbox
- [Mem0](https://agentstackdirectory.com/tools/mem0/): Memory layer that lets agents learn from past interactions. Official site: https://mem0.ai/
- [Zep](https://agentstackdirectory.com/tools/zep/): Context layer that unifies business data, documents, and chats for agents. Official site: https://www.getzep.com/
- [Letta](https://agentstackdirectory.com/tools/letta/): Platform for stateful agents that keep long-term memory. Official site: https://www.letta.com/
- [Cognee](https://agentstackdirectory.com/tools/cognee/): Open-source agent memory platform built on graph and vector stores. Official site: https://www.cognee.ai/
- [Supermemory](https://agentstackdirectory.com/tools/supermemory/): Memory and continual learning engine for agents. Official site: https://supermemory.ai/
- [Exa](https://agentstackdirectory.com/tools/exa/): Search API built for AI agents, with real-time web data and deep research. Official site: https://exa.ai/
- [Tavily](https://agentstackdirectory.com/tools/tavily/): Real-time search and content extraction APIs for agents. Official site: https://www.tavily.com/
- [Firecrawl](https://agentstackdirectory.com/tools/firecrawl/): Turns websites into clean, LLM-ready data with crawl, scrape, and search APIs. Official site: https://www.firecrawl.dev/
- [Jina Reader](https://agentstackdirectory.com/tools/jina-reader/): Converts any URL to Markdown for grounding LLMs. Official site: https://jina.ai/reader
- [Brave Search API](https://agentstackdirectory.com/tools/brave-search-api/): Independent web search API covering a 40B+ page index. Official site: https://brave.com/search/api
- [Apify](https://agentstackdirectory.com/tools/apify/): Marketplace of ready-made scrapers and automation tools callable by agents. Official site: https://apify.com/
- [Parallel](https://agentstackdirectory.com/tools/parallel/): Web search, extraction, and monitoring APIs built for AI. Official site: https://parallel.ai/
- [AgentMail](https://agentstackdirectory.com/tools/agentmail/): Email inbox API for agents: create, send, and receive real inboxes. Official site: https://www.agentmail.to/
- [Resend](https://agentstackdirectory.com/tools/resend/): Developer email API for transactional and marketing mail. Official site: https://resend.com/
- [Mailgun](https://agentstackdirectory.com/tools/mailgun/): Email API to send, receive, and track email. Official site: https://www.mailgun.com/
- [Composio](https://agentstackdirectory.com/tools/composio/): Tool calls with delegated auth across 1,500+ apps for agents. Official site: https://composio.dev/
- [Pipedream Connect](https://agentstackdirectory.com/tools/pipedream-connect/): Managed auth and thousands of prebuilt tools across 3,000+ APIs. Official site: https://pipedream.com/connect
- [Arcade](https://agentstackdirectory.com/tools/arcade/): Actions runtime that lets agents act on users' behalf with governed auth. Official site: https://www.arcade.dev/
- [Nango](https://agentstackdirectory.com/tools/nango/): Integration platform connecting products and agents to 1,000+ APIs. Official site: https://nango.dev/
- [Smithery](https://agentstackdirectory.com/tools/smithery/): Registry and hosting to connect agents to MCP tools and services. Official site: https://smithery.ai/
- [Stripe Agent Toolkit](https://agentstackdirectory.com/tools/stripe-agent-toolkit/): Stripe's MCP server, plugins, and skills for agents that handle payments. Official site: https://docs.stripe.com/agents
- [Skyfire](https://agentstackdirectory.com/tools/skyfire/): Identity and payment credentials for AI agents on the open web. Official site: https://skyfire.xyz/
- [Coinbase x402](https://agentstackdirectory.com/tools/coinbase-x402/): Open standard for internet-native payments using HTTP 402, built for agents. Official site: https://x402.org/
- [Vapi](https://agentstackdirectory.com/tools/vapi/): Developer platform to build, test, and deploy voice AI agents. Official site: https://vapi.ai/
- [Retell AI](https://agentstackdirectory.com/tools/retell-ai/): Voice agents for inbound and outbound phone calls. Official site: https://www.retellai.com/
- [ElevenLabs Agents](https://agentstackdirectory.com/tools/elevenlabs-agents/): Build and deploy chat and voice agents on ElevenLabs. Official site: https://elevenlabs.io/agents
- [Langfuse](https://agentstackdirectory.com/tools/langfuse/): Open-source tracing, evals, and observability for agents. Official site: https://langfuse.com/
- [LangSmith](https://agentstackdirectory.com/tools/langsmith/): LangChain's tracing and monitoring platform for agents and LLM apps. Official site: https://www.langchain.com/langsmith/observability
- [Helicone](https://agentstackdirectory.com/tools/helicone/): AI gateway with routing and LLM observability. Official site: https://www.helicone.ai/
- [AgentOps](https://agentstackdirectory.com/tools/agentops/): Tracing and debugging for AI agents. Official site: https://www.agentops.ai/
- [Braintrust](https://agentstackdirectory.com/tools/braintrust/): Observability and evals platform for production agents. Official site: https://www.braintrust.dev/
- [Mastra](https://agentstackdirectory.com/tools/mastra/): TypeScript framework for agents with memory, tools, MCP, and workflows. Official site: https://mastra.ai/
- [Vercel AI SDK](https://agentstackdirectory.com/tools/vercel-ai-sdk/): Unified TypeScript SDK for AI apps and agents across model providers. Official site: https://ai-sdk.dev/
- [OpenAI Agents SDK](https://agentstackdirectory.com/tools/openai-agents-sdk/): OpenAI's lightweight Python framework for multi-agent workflows. Official site: https://openai.github.io/openai-agents-python
- [LangGraph](https://agentstackdirectory.com/tools/langgraph/): Agent orchestration framework with durable execution and human-in-the-loop. Official site: https://www.langchain.com/langgraph
- [CrewAI](https://agentstackdirectory.com/tools/crewai/): Framework and platform for multi-agent teams. Official site: https://crewai.com/
- [Pydantic AI](https://agentstackdirectory.com/tools/pydantic-ai/): Type-safe Python agent framework from the Pydantic team. Official site: https://pydantic.dev/docs/ai/overview
- [Auth0 for AI Agents](https://agentstackdirectory.com/tools/auth0-for-ai-agents/): Auth0 tools for user login, token vaults, and permissions in AI agents. Official site: https://auth0.com/solutions/ship-ai-agents
- [Agent 37](https://agentstackdirectory.com/tools/agent-37/): Cloud sandboxes for running AI agents, positioned as lower-cost agent infrastructure. Official site: https://www.agent37.com/
- [Pickle Browser](https://agentstackdirectory.com/tools/pickle-browser/): Local browser that opens real pages for agents, shows its work on your machine, and needs no account. Official site: https://picklebrowser.com/
- [AIO Sandbox](https://agentstackdirectory.com/tools/aio-sandbox/): All-in-one agent sandbox with browser, shell, file access, VSCode Server, and MCP in one container. Official site: https://sandbox.agent-infra.com/

## Guides
- [Best cloud browsers for AI agents](https://agentstackdirectory.com/guides/best-cloud-browsers-for-ai-agents/)
- [Best code sandboxes for AI agents](https://agentstackdirectory.com/guides/best-code-sandboxes-for-ai-agents/)
- [Best memory layers for AI agents](https://agentstackdirectory.com/guides/best-memory-layers-for-ai-agents/)
- [Best search and web data APIs for AI agents](https://agentstackdirectory.com/guides/best-search-apis-for-ai-agents/)
- [Best email APIs for AI agents](https://agentstackdirectory.com/guides/best-email-apis-for-ai-agents/)
- [Best tool integration platforms for AI agents](https://agentstackdirectory.com/guides/best-integration-platforms-for-ai-agents/)
- [Best payment tools for AI agents](https://agentstackdirectory.com/guides/best-payment-tools-for-ai-agents/)
- [Best voice agent platforms](https://agentstackdirectory.com/guides/best-voice-agent-platforms/)
- [Best observability and eval tools for AI agents](https://agentstackdirectory.com/guides/best-observability-tools-for-ai-agents/)
- [Best AI agent frameworks](https://agentstackdirectory.com/guides/best-ai-agent-frameworks/)
- [Best open-source infrastructure for AI agents](https://agentstackdirectory.com/guides/best-open-source-agent-infrastructure/)

## Alternatives pages
- One page per tool at https://agentstackdirectory.com/alternatives/<tool-slug>/ (e.g. https://agentstackdirectory.com/alternatives/e2b/).

## Site
- [Sponsor](https://agentstackdirectory.com/sponsor/): sitewide $499/month, category $299/month (one per category), Founding Partner $1,500 for 12 months (max 10), newsletter $149/issue, weekly trial $149.
- [Submit](https://agentstackdirectory.com/submit/): free listing; $79 fast-track review (refunded if declined); featured $99/month; launch package $299.
- [Claim](https://agentstackdirectory.com/claim/): vendors claim their listing for free.
- [Badge](https://agentstackdirectory.com/badge/): free optional badge for listed tools.
- [Data](https://agentstackdirectory.com/data.json): full listing data as JSON, licensed CC BY 4.0.
- [MCP server](https://agentstackdirectory.com/mcp/): free remote MCP endpoint at https://agentstackdirectory.com/mcp (Streamable HTTP) with tools search_tools, get_tool, compare, list_categories.