# Agent Stack Directory

> A checked directory of 84 infrastructure tools for AI agents across 13 categories. Free to browse, no signup. Paid placements are labeled and never change organic order.

## New this week
- [Desearch](https://agentstackdirectory.com/tools/desearch/): Search API for AI agents: one API key covers web search, AI search with source links, page extraction to clean text or markdown, and X search. REST API, Python and JavaScript SDKs, and a hosted MCP server. Usage-based pricing. Official site: https://desearch.ai/
- [Tokenrip](https://agentstackdirectory.com/tools/tokenrip/): Shared workspace your AI agents work from: files with version history, tables, tasks any agent can pick up, and pinned decisions every agent reads when it loads the workspace. Agents connect from Claude, ChatGPT, Codex, Cursor or any MCP app through a hosted MCP server, a CLI or an HTTP API, each with its own revocable key, and every change is logged with the agent that made it. Official site: https://tokenrip.com/
- [Browserless](https://agentstackdirectory.com/tools/browserless/): Cloud browser automation platform: connect Puppeteer, Playwright or Selenium to managed headless browsers, or use BrowserQL, REST APIs and an MCP server for scraping, screenshots, PDFs and AI-driven browsing. Self-hosting available, with a paid license for commercial use. Official site: https://www.browserless.io/
- [Lightpanda](https://agentstackdirectory.com/tools/lightpanda/): Open-source headless browser written from scratch in Zig for automation, crawling and AI agents: runs JavaScript without graphical rendering, works with Puppeteer and Playwright over CDP, with a hosted cloud option. Official site: https://lightpanda.io/
- [MemorySync](https://agentstackdirectory.com/tools/memorysync/): MemorySync is a memory API for AI applications: your agent writes what it learns about each user, and MemorySync returns the relevant parts later, ranked by meaning and scoped to that user. Official site: https://memorysync.io/
- [MepMail](https://agentstackdirectory.com/tools/mepmail/): Email for apps and AI agents: a Resend-compatible sending API with SMTP, plus mailboxes on your own domain that agents read and draft in over MCP, where you choose direct sending or approval for each reply. AGPL open source and self-hostable. Official site: https://mepmail.dev/
- [MachineMail](https://agentstackdirectory.com/tools/machinemail/): Email API for AI agents: free inboxes on a shared domain or your own, a trust report on every inbound message, a REST API that follows AgentMail's paths and field names, webhooks and an MCP server. Official site: https://machinemail.dev/
- [Runtime](https://agentstackdirectory.com/tools/runtime/): Linux sandboxes for agent code, each a Firecracker microVM, billed on active CPU, with pause, forks, snapshots, custom images, an MCP server and SDKs. Official site: https://withruntime.com/

## Categories
- [Browsers & Computer Use](https://agentstackdirectory.com/category/browsers/): Cloud browsers and SDKs that let agents use the web. 10 tools.
- [Code Sandboxes](https://agentstackdirectory.com/category/sandboxes/): Isolated machines where agents can safely run code. 13 tools.
- [Memory & Context](https://agentstackdirectory.com/category/memory/): Long-term memory layers so agents remember users and tasks. 8 tools.
- [Search & Web Data](https://agentstackdirectory.com/category/search/): APIs that give agents fresh web search and clean page content. 9 tools.
- [Email](https://agentstackdirectory.com/category/email/): Inboxes and sending APIs for agents that talk over email. 6 tools.
- [Integrations & Auth Tools](https://agentstackdirectory.com/category/integrations/): Prebuilt tool calls and managed OAuth for thousands of apps. 6 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. 6 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.
- [Durable Execution](https://agentstackdirectory.com/category/durable/): Workflow engines that let long-running agents resume after a crash. 6 tools.
- [Model Gateways](https://agentstackdirectory.com/category/gateways/): One API in front of many models, with routing, fallbacks and spend controls. 7 tools.

## 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. Its public GitHub repo is archived: core development moved to a private codebase in June 2026. 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/
- [Aident Loadout](https://agentstackdirectory.com/tools/aident-loadout/): Capability layer connecting agents to 1,000+ apps and 27,000+ actions, with a credential vault, audit log, CLI and MCP server. Official site: https://aident.ai/
- [Cosmonic](https://agentstackdirectory.com/tools/cosmonic/): WebAssembly sandboxes for agent code, MCP servers and tools, with no access until you grant it: the free Cosmonic Desktop app (public beta) and Cosmonic Control for Kubernetes. Open source core: CNCF wasmCloud. Official site: https://cosmonic.com/
- [VoidRun](https://agentstackdirectory.com/tools/voidrun/): Isolated microVM sandboxes where AI agents and developers run untrusted code, via REST API, TypeScript and Python SDKs, and an MCP server (beta). Official site: https://void-run.com/
- [Celesto](https://agentstackdirectory.com/tools/celesto/): Hardware-isolated cloud computers for AI agents, with browser, desktop, shell and file access, pause, resume and forking, via CLI and SDK; Apache-2.0 microVM core you can self-host. Official site: https://celesto.ai/
- [Shipmail](https://agentstackdirectory.com/tools/shipmail/): Business email hosting with an API for agents: custom-domain mailboxes agents can send from and read, webhooks, TypeScript and Python SDKs, a CLI and an MCP server. Official site: https://shipmail.to/
- [MachineMail](https://agentstackdirectory.com/tools/machinemail/): Email API for AI agents: free inboxes on a shared domain or your own, a trust report on every inbound message, a REST API that follows AgentMail's paths and field names, webhooks and an MCP server. Official site: https://machinemail.dev/
- [Sandbox0](https://agentstackdirectory.com/tools/sandbox0/): Cloud computers for AI agents that keep the whole writable root filesystem, pause compute between tasks and resume on demand, via API, SDKs and CLI. Official site: https://sandbox0.ai/
- [Runtime](https://agentstackdirectory.com/tools/runtime/): Linux sandboxes for agent code, each a Firecracker microVM, billed on active CPU, with pause, forks, snapshots, custom images, an MCP server and SDKs. Official site: https://withruntime.com/
- [Pragor](https://agentstackdirectory.com/tools/pragor/): Operations board for teams of AI agents: shared tasks and messages, human approvals for risky steps, an attributable audit trail, app health reporting and an MCP server, across any framework or model. Official site: https://pragor.net/
- [Temporal](https://agentstackdirectory.com/tools/temporal/): Open-source durable execution platform where you write workflows as code and they pick up where they left off after a failure. Official site: https://temporal.io/
- [Inngest](https://agentstackdirectory.com/tools/inngest/): Durable execution for background jobs, workflows, and AI agents, with automatic retries, flow control, and step-level observability. Official site: https://www.inngest.com/
- [Trigger.dev](https://agentstackdirectory.com/tools/trigger-dev/): Open-source platform for durable AI agents and workflows in TypeScript, with long-running tasks, retries, queues, and LLM observability. Official site: https://trigger.dev/
- [Restate](https://agentstackdirectory.com/tools/restate/): Runtime for agents and backends with durable execution, state, queues, RPC, timers, and flow control in one binary. Official site: https://restate.dev/
- [DBOS](https://agentstackdirectory.com/tools/dbos/): Open-source durable execution and workflow orchestration system. Official site: https://www.dbos.dev/
- [Hatchet](https://agentstackdirectory.com/tools/hatchet/): One platform to orchestrate AI agents, schedule background tasks, and run workflows. Official site: https://hatchet.run/
- [OpenRouter](https://agentstackdirectory.com/tools/openrouter/): One API for many models from many providers, with model and price comparison. Official site: https://openrouter.ai/
- [LiteLLM](https://agentstackdirectory.com/tools/litellm/): AI gateway and LLM proxy: one OpenAI-compatible key for 140+ providers, with spend tracking, caps and routing. Self-hostable. Official site: https://www.litellm.ai/
- [Portkey](https://agentstackdirectory.com/tools/portkey/): AI gateway and production stack for teams shipping generative AI apps, with an open-source gateway. Official site: https://portkey.ai/
- [Cloudflare AI Gateway](https://agentstackdirectory.com/tools/cloudflare-ai-gateway/): Analytics, caching, rate limiting and model fallback in front of your AI provider calls. Official site: https://developers.cloudflare.com/ai-gateway/
- [Vercel AI Gateway](https://agentstackdirectory.com/tools/vercel-ai-gateway/): Use 400+ AI models through one endpoint without managing rate limits and API keys per provider. Official site: https://vercel.com/ai-gateway
- [Kong AI Gateway](https://agentstackdirectory.com/tools/kong-ai-gateway/): Security, routing, observability and cost control for LLM and MCP traffic, from the Kong API gateway team. Official site: https://konghq.com/products/kong-ai-gateway
- [Requesty](https://agentstackdirectory.com/tools/requesty/): OpenAI-compatible LLM router for 600+ models with smart routing, caching, failover and EU data residency. Official site: https://www.requesty.ai/
- [Xquik](https://agentstackdirectory.com/tools/xquik/): X (Twitter) data API and MCP server for searching tweets, profiles and followers. Usage-based billing; independent of X Corp. Official site: https://xquik.com/
- [ContextNest](https://agentstackdirectory.com/tools/contextnest/): Versioned markdown context vault for agents, read through a CLI or an MCP server. Official site: https://promptowl.ai/contextnest/
- [MepMail](https://agentstackdirectory.com/tools/mepmail/): Email for apps and AI agents: a Resend-compatible sending API with SMTP, plus mailboxes on your own domain that agents read and draft in over MCP, where you choose direct sending or approval for each reply. AGPL open source and self-hostable. Official site: https://mepmail.dev/
- [MemorySync](https://agentstackdirectory.com/tools/memorysync/): MemorySync is a memory API for AI applications: your agent writes what it learns about each user, and MemorySync returns the relevant parts later, ranked by meaning and scoped to that user. Official site: https://memorysync.io/
- [Browserless](https://agentstackdirectory.com/tools/browserless/): Cloud browser automation platform: connect Puppeteer, Playwright or Selenium to managed headless browsers, or use BrowserQL, REST APIs and an MCP server for scraping, screenshots, PDFs and AI-driven browsing. Self-hosting available, with a paid license for commercial use. Official site: https://www.browserless.io/
- [Lightpanda](https://agentstackdirectory.com/tools/lightpanda/): Open-source headless browser written from scratch in Zig for automation, crawling and AI agents: runs JavaScript without graphical rendering, works with Puppeteer and Playwright over CDP, with a hosted cloud option. Official site: https://lightpanda.io/
- [Desearch](https://agentstackdirectory.com/tools/desearch/): Search API for AI agents: one API key covers web search, AI search with source links, page extraction to clean text or markdown, and X search. REST API, Python and JavaScript SDKs, and a hosted MCP server. Usage-based pricing. Official site: https://desearch.ai/
- [Tokenrip](https://agentstackdirectory.com/tools/tokenrip/): Shared workspace your AI agents work from: files with version history, tables, tasks any agent can pick up, and pinned decisions every agent reads when it loads the workspace. Agents connect from Claude, ChatGPT, Codex, Cursor or any MCP app through a hosted MCP server, a CLI or an HTTP API, each with its own revocable key, and every change is logged with the agent that made it. Official site: https://tokenrip.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/)

## Pricing tables
- [Pricing tables](https://agentstackdirectory.com/pricing/): free tier, starting paid price, unit and vendor source link for 23 browsers and sandboxes, as listed on vendor sites between Oct 19, 2026 and Oct 29, 2026.
- [Browsers & Computer Use pricing](https://agentstackdirectory.com/pricing/browsers/)
- [Code Sandboxes pricing](https://agentstackdirectory.com/pricing/sandboxes/)

## 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.
- [About and methodology](https://agentstackdirectory.com/about/): run by Shawn G in Miami; how tools are checked.
- [Privacy](https://agentstackdirectory.com/privacy/): no cookies, no ad trackers.
- Contact: hello@agentstackdirectory.com. Sponsors: sponsors@agentstackdirectory.com.
- [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.