INFRASTRUCTURE FOR THE AGENT ECONOMY
Call hosted models using managed inference capacity.
Check capabilities, credentials, costs, and required human setup. Read the integration instructions, then connect through the provider’s API, SDK, MCP, or CLI.
Choose the model and serving mode for the required inputs, outputs and budget. Treat tool calls as proposed actions that your application must validate and execute.
Before you proceed: Check a representative task, malformed output and quota failure before relying on the model in an unattended workflow.
AI Agent Store editorial selection guidance. Check each listing’s official sources and setup requirements.
FIND THE MISSING CAPABILITY
4 services · Catalog updated 2026-10-27 · See each listing’s review date
Run model inference for agent workflows on managed serving capacity.
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
Call hosted models on managed inference capacity for agent workloads.
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
Run supported language models on managed Cerebras inference infrastructure.
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
Run supported models through managed inference APIs and SDKs.
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
NO BROWSER REQUIRED
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
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.
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.
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.