249 listed

Agent infrastructure

The services agents run on: memory, code sandboxes, browsers, voice, search and scraping APIs, vector databases, LLM gateways, inference, durable execution and hosting. Facts such as self-hosting and compliance come from each vendor's own pages, with links.

Showing 1–21 of 21

0.801score
E2B
E2B
Open-source infrastructure that runs AI-generated code in isolated cloud sandboxes.
InfrastructureAFreshness: A★ 14.5Ksandbox
0.795score
OpenSandbox
OpenSandbox (Alibaba)
Open-source sandbox platform that runs AI agent workloads in isolated environments on your own infrastructure.
InfrastructureAFreshness: A★ 16.1Ksandbox
0.767score
Microsandbox
Super Rad Company
Open-source, local microVM sandboxes for untrusted workloads, with an embeddable SDK and an MCP server.
InfrastructureAFreshness: A★ 8.8Ksandbox
0.735score
Kubernetes Agent Sandbox
Kubernetes SIG Apps
Kubernetes CRD and controller for isolated, stateful sandbox pods that behave like single-container VMs.
InfrastructureAFreshness: A★ 4.4Ksandbox
0.723score
Beam Sandboxes
Beam
CPU and GPU machines and sandboxes for agents, billed by the millisecond, with VMs that pause with memory intact.
InfrastructureAFreshness: A★ 1.8Ksandbox
0.703score
Cloudflare Sandbox SDK
Cloudflare
Sandboxes on Cloudflare Workers that run untrusted or agent-written code in isolated containers.
InfrastructureAFreshness: A★ 1.2Ksandbox
0.671score
Vercel Sandbox
Vercel
Isolated Linux microVMs for running agent-generated or untrusted code, driven by an SDK and CLI.
InfrastructureAFreshness: A★ 215sandbox
0.599score
Riza
Riza
Code execution API that lets LLM-generated code run in isolation and returns its output.
InfrastructureAFreshness: Asandbox
0.599score
Runloop
Runloop
Isolated Linux devboxes for running AI agents and their code, with snapshots and reusable blueprints.
InfrastructureAFreshness: Asandbox
0.597score
Amazon Bedrock AgentCore Code Interpreter
Amazon Web Services
Managed AWS sandbox where AI agents write and run code, with pre-built language runtimes and file handling.
InfrastructureAFreshness: Asandbox
0.595score
Blaxel
Blaxel
Perpetual sandboxes that idle to standby and resume in about 25 milliseconds, with shared agent storage.
InfrastructureAFreshness: Asandbox
0.595score
Modal Sandboxes
Modal
Serverless sandboxes that let agents run untrusted code with fast starts, snapshots and egress controls.
InfrastructureAFreshness: Asandbox
0.594score
Deno Sandbox
Deno
Instant Linux microVMs on Deno Deploy for running untrusted code, driven from an SDK.
InfrastructureAFreshness: Asandbox
0.594score
Docker Sandboxes
Docker
Runs AI coding agents in isolated sandboxes on a developer machine or in Docker-managed cloud, managed with the sbx CLI.
InfrastructureAFreshness: Asandbox
0.592score
Northflank Sandboxes
Northflank
Secure microVM and gVisor sandboxes for untrusted and agent-generated code, on Northflank Cloud or your own cloud.
InfrastructureAFreshness: Asandbox
0.591score
Freestyle
Freestyle
Full Linux VMs for long-running agent tasks, with millisecond startup, live cloning and pause and resume.
InfrastructureAFreshness: Asandbox
0.587score
Morph Cloud
Morph Labs
Platform for creating and managing VM-based remote runtimes for AI agents, with snapshots, SSH and a Python SDK.
InfrastructureAFreshness: Asandbox
0.579score
Sprites
Fly.io
Persistent, hardware-isolated Linux VMs for AI agents that hibernate when idle and wake quickly.
InfrastructureAFreshness: Asandbox
0.554score
Daytona
Daytona
Secure, elastic infrastructure that runs AI-generated code in sandboxes created in under 90 milliseconds.
InfrastructureAFreshness: A★ 15sandbox
0.535score
Together Sandbox
Together AI
Code sandboxes built from Docker-image snapshots for running agent and model-generated code, with Python and TypeScript SDKs.
InfrastructureAFreshness: A★ 3sandbox
0.446score
Azure Container Apps Dynamic Sessions
Microsoft
Hyper-V isolated code interpreter sessions in Azure Container Apps for running LLM-generated or untrusted code.
InfrastructureAFreshness: Asandbox