Best agent-infrastructure Tools

Schedule tasks for AI agents straight from Google Calendar, with agents that connect to tools like Gmail, Slack, Notion, GitHub, and more.

Key Features:

Open-source file-transfer and identity infrastructure for AI agents in one Go binary: each agent gets an address, folder, inbox, and API key in a single call, with 5 GB transfers, signed receipts, and an MCP bridge.

Key Features:

An open-source control plane for unattended LLM agents and workflows, enforcing cost caps, human approval gates, model-switching policies, and self-healing rollbacks around agents you build.

Key Features:

Cloudflare’s developer framework for building, deploying, and running agents close to web infrastructure on Workers and related services.

Key Features:

Open-source sandbox service from Tencent Cloud that spins up hardware-isolated micro-VMs for AI agents in under 60ms, with E2B SDK compatibility for drop-in migration.

Key Features:

Open-source secure code-execution sandbox for AI agents — spin up a fresh Linux VM in under 200ms, hand your agent a Python/Node/Bash environment, and get back files, plots, and results without ever exposing your infrastructure.

Key Features:

• •Hardware-level security isolation
• •Sub-150ms sandbox startup
• •Multi-language runtime support

Managed browser infrastructure purpose-built for AI agents — spin up isolated Chrome sessions in seconds, with recording, captcha handling, and persistent state.

Key Features:

• •Managed Chrome sessions accessible over CDP, Playwright, Puppeteer
• •Automatic Cloudflare / hCaptcha solving
• •Residential proxy rotation with per-country targeting

Free, local-first AI gateway that routes any coding tool to 237 LLM providers with auto-fallback, token compression, and MCP support.

Key Features:

• •Protocol translation across OpenAI/Claude/Gemini/Responses
• •Combos and auto model variants
• •Stacked RTK + Caveman token compression

Alibaba's open-source, in-page JavaScript framework that gives any web page its own natural-language GUI agent with one script.

Key Features:

• •In-page JavaScript agent
• •Text-DOM operation without screenshots
• •Bring-your-own LLM

Sanbox by Sanlabs runs AI agents in isolated, resumable MicroVM sandboxes with persistent filesystems, live run events, network ACLs, and self-hosting options.

Key Features:

A declarative, sandboxed, non-Turing-complete language and runtime that lets AI agents crystallize learned procedures into auditable, reusable skills.

Key Features:

A payments and identity network designed to let software agents pay for services and prove who they are during automated transactions.

Key Features:

An open-source platform for building durable, observable agent workflows that can invoke application functions while preserving operational control.

Key Features:

Monid is a metered agent-tool registry that lets AI agents discover, compare, and invoke more than 1,700 tools from over 55 providers through a skill, remote MCP server, or command-line interface using one shared balance.

Key Features: