agent-exec logo
BUZZ: 23%

Pay-per-use code execution for AI agents. HTTP 402, no account, no API key.

18Views

agent-exec Overview

agent-exec runs untrusted source code for software agents and returns stdout, stderr and the exit code from an isolated, network-less sandbox. There is no signup, no account and no API key: it answers HTTP 402 Payment Required with an x402 challenge, and possession of a valid payment is the entire authorisation model, so an agent can discover the price, pay it and get a result with no human in the loop. Every endpoint is priced per call in USDC on Base, from $0.0010 for POST /execute. It also offers the small paid primitives agents need to coordinate: object storage, name claims, attestations, handoffs and dead-man switches. The whole surface is machine-readable up front - x402 manifest, OpenAPI 3 and llms.txt.

How to evaluate agent-exec for sandboxes workflows

agent-exec is listed as a paid sandboxes AI agent with api access. Use this page to compare its core capabilities, practical use cases, pricing model, and alternatives before adding it to your workflow.

A strong first-fit use case is An autonomous agent needs to run code it just wrote and read the real output, especially if your team is shortlisting sandboxes tools for a specific operational need.

Best-fit checks before choosing:

  • Confirm that paid pricing matches your expected usage volume.
  • Compare agent-exec with similar sandboxes AI agents in the alternatives section.
  • Validate the key capability: Accountless: no signup, no API key, no dashboard - a valid x402 payment is the only credential.

agent-exec Key Features

Accountless: no signup, no API key, no dashboard - a valid x402 payment is the only credential
HTTP 402 native, priced per call in USDC on Base from $0.0010
Isolated, network-less sandbox returning stdout, stderr and exit code
Machine-readable discovery: x402 manifest, OpenAPI 3 and llms.txt
Paid coordination primitives: storage, claims, attestation, handoff, dead-man switch

agent-exec Use Cases

An autonomous agent needs to run code it just wrote and read the real output
Executing untrusted or model-generated code away from your own host
Paying for compute machine-to-machine without provisioning an account
Giving a short-lived agent scratch storage and a name claim it can pay for per use
Integrating a priced tool purely from its published discovery documents

Quick Facts

CategorySandboxes
IndustryHorizontal
AccessAPI
Pricing
Paid
StatusStandard
ListedSep 13, 2026
Popularity23%
Loading featured agents...

Popular Categories

View All
Loading latest articles...

Newsletter

Stay Ahead of the Curve

Get curated AI agent updates delivered to your inbox

No spam. Unsubscribe anytime.