E2B ↗
Run your code in an isolated execution environment.
Before you connect
Provision an API key and approve the compute budget.
Our integration playbook
Treat the sandbox lifecycle as part of the task
INFRASTRUCTURE FOR THE AGENT ECONOMY
Compute services for AI agents
Allocate an execution environment for your workload.
Check capabilities, credentials, costs, and required human setup. Read the integration instructions, then connect through the provider’s API, SDK, MCP, or CLI.
100 available services15 capability categoriesOpen discovery · no login
Choosing compute for your task
Choose resources for a bounded job and define when they should stop. Make resource cleanup part of the failure path as well as the success path.
Before you proceed: Track idle environments against the approved usage budget.
AI Agent Store editorial selection guidance. Check each listing’s official sources and setup requirements.
FIND THE MISSING CAPABILITY
Services with Compute
9 services · Catalog updated 2026-10-27 · See each listing’s review date
Daytona ↗
Provision an isolated cloud computer for your code and tools.
Before you connect
Create a Daytona organization, provision an API key and approve resource usage and billing.
Our integration playbook
Make sandbox cleanup part of your result
Modal Sandboxes ↗
Allocate isolated compute for generated code and custom dependencies.
Before you connect
Create a Modal account and workspace, configure credentials, and authorize the compute budget and any required secrets.
Our integration playbook
Budget the environment before executing generated code
Railway ↗
Deploy and inspect application infrastructure through agent tools.
Before you connect
Create a Railway account, choose a workspace and billing plan, and authorize the projects the agent may access. Connect application source and configure required secrets before deployment.
Our integration playbook
Bind the deployment to a project, environment and source revision
Cloudflare ↗
Operate hosted compute and account resources through the Cloudflare API MCP server.
Before you connect
Create a Cloudflare account, choose the services and billing plans required by the workload, and authorize only the accounts and resources the agent should operate.
Our integration playbook
Resolve account and resource identity before executing a discovered operation
Fireworks AI ↗
Run model inference for agent workflows on managed serving capacity.
Before you connect
Create a Fireworks account and API key, configure billing and choose a supported model and serving mode. Set an application budget and decide which tools the model may propose.
Our integration playbook
Separate model inference from permission to execute a tool
Together AI ↗
Call hosted models on managed inference capacity for agent workloads.
Before you connect
Create an account and project, generate an API key, configure billing and choose the exact model and serving mode. Define the request budget and validate the model on the intended task.
Our integration playbook
Choose the serving mode before committing to a latency-sensitive workflow
Cerebras Inference ↗
Run supported language models on managed Cerebras inference infrastructure.
Before you connect
Create a Cloud Console organization and project, issue an API key and configure billing. Select an available model and check its capabilities, project limits and serving option.
Our integration playbook
Budget output tokens against both inference spend and available quota
Groq ↗
Run supported models through managed inference APIs and SDKs.
Before you connect
Create a Groq account and API key. Choose an available model and configure the organization’s tier, payment method and spend limits before production use.
Our integration playbook
Coordinate model calls across agents sharing one organization
Explore related capabilities
Browse all service tags →NO BROWSER REQUIRED
Discover. Inspect.
Connect.
Search for a capability, then follow the listing’s siteGuide link for our original integration playbook: selection advice, workflow, acceptance checks and recovery steps. The complete playbook is in the page HTML, so you can fetch it without JavaScript or a login.
GET /api/agent-services?capability=email GET /api/agent-services?interface=mcp GET /api/agent-services?payment=x402-wallet GET /api/agent-services?payment=mpp-wallet GET /api/agent-services?payment=no-payment GET /api/agent-services?id=e2b
Full catalog: /data/agent-services.json
Manifest: /.well-known/agent-services.json
Choose your next service with the facts in hand.
Find the tools you need
You are here to get something done. Find a mailbox for your messages, a browser for your web tasks, a sandbox for your code, or a wallet for approved payments.
Check what you need from your owner
Inspect the setup requirements before connecting. You may need your owner to create an account, grant OAuth consent, fund a wallet, or provide a website login.
Confirm your payment path
Check whether usage is free, billed to a provider account or uses a documented x402 or MPP wallet. “Not verified” means agent payment support has not been established. Confirm current terms and stay within your owner’s approved budget.