Agent Infrastructure

Unified infrastructure primitives for AI agents — sandboxes, browsers, code execution, and file systems — with integrated billing, auth, and observability.

What is Agent Infrastructure?

AI agents need more than just LLM calls. They need to execute code, browse the web, manipulate files, and interact with the real world. Today, wiring up these capabilities means juggling multiple providers, billing accounts, and auth systems.

Transactional provides four core infrastructure primitives purpose-built for AI agents, unified under a single API key, billing account, and observability layer.

The Four Primitives

PrimitiveWhat It DoesPowered By
SandboxesIsolated execution environments (microVMs)E2B (Firecracker)
BrowsersHeadless browser sessions for web interactionBrowserbase (Chromium)
Code ExecutionSecure multi-language script executionPiston (self-hosted)
File SystemsPersistent file storage for agent workspacesS3-compatible storage

Why Transactional?

Building agent infrastructure from scratch means integrating, billing, and monitoring each provider independently. Transactional wraps best-in-class providers into a single developer experience.

Without TransactionalWith Transactional
Separate accounts for E2B, Browserbase, S3One API key for everything
Multiple billing dashboardsUnified billing with per-agent cost breakdown
No cross-provider authSingle auth layer across all primitives
Build your own loggingFull observability via Observability
Manual integration workComposable primitives that work together

Build vs. Buy

We deliberately chose best-in-class providers for each primitive rather than building everything from scratch:

  • Sandboxes — E2B's Firecracker microVMs deliver sub-200ms cold starts with battle-tested isolation
  • Browsers — Browserbase provides managed Chromium with stealth mode and anti-detection built in
  • Code Execution — Piston is self-hosted for full control over language runtimes and resource limits
  • File Systems — S3-compatible storage gives S3-compatible storage with zero egress fees

Integration with Existing Modules

Agent primitives are designed to compose with the rest of the Transactional platform:

  • AI Gateway — Route LLM calls through the gateway for caching, failover, and cost tracking while your agent uses sandboxes and browsers
  • Memory — Persist agent context and conversation history across sessions
  • Observability — Every sandbox creation, browser action, and code execution is automatically traced
  • Email — Agents can send emails as part of their workflow using the same API
  • Auth — Authenticate agent sessions with the same auth infrastructure your users use

The Composition Model

The real power is combining primitives. A single agent can:

  1. Receive a task via your app
  2. Spin up a sandbox to install dependencies and run complex scripts
  3. Open a browser to research information on the web
  4. Execute quick code snippets to transform data
  5. Store results in a file system workspace
  6. Send a summary email to the user

All under one API key, one bill, one trace.

Getting Started