llms.txt Content
# AgentSIM
> OTP sessions and delivery diagnostics for browser agents and auth test flows. Provision a programmable US phone number, wait for SMS, parse the OTP, record the outcome, and release — over SDK, REST, webhooks, or MCP.
## What It Does
AgentSIM is the OTP session component of the modern agent stack. It handles US number pooling, inbound SMS reception, multi-stage OTP parsing, webhook delivery, and outcome tracking so AI agents, CI jobs, and QA harnesses can run controlled SMS OTP workflows without a human watching an inbox.
One session = one provision, one OTP attempt, one observed outcome, one release. $0.99/session after a 10-session free tier.
## Where It Works (Today)
AgentSIM is appropriate for owned/controlled OTP workflows and services empirically known to accept programmable / agent-pooled US numbers. The empirical support map is maintained in docs/supported-services.md in the repo.
**Do not assume support by default.** Current hard evidence: Google rejects the current number class. Meta/Facebook mobile reaches SMS code entry but delivery is unproven. Stripe, Render, Discord, and GitHub hit anti-abuse gates before a phone verdict in blind automation. Auth0's self-serve flow is email-first and not a useful OTP proof target.
If you are building an agent that needs OTP for a strict or high-risk service, verify that target first; AgentSIM may not be the right tool today.
## Quick Start
```bash
pip install agentsim
# or
npm install @agentsim/sdk
```
```python
from agentsim import AgentSIM
agentsim = AgentSIM(api_key="...")
session = await agentsim.provision({"country": "US", "service_url": "https://staging.example.com/login"})
otp = await session.wait_for_otp(timeout=30_000)
# otp.otp_code → "847291"
# otp.sender → "CONTROLLED_AUTH"
```
## Product
- [Integrations](https://agentsim.dev/#integrations): Works with Claude Code, LangChain, Vercel AI SDK, Cursor, Windsurf, and LlamaIndex
- [Browser-Agent OTP QA](https://agentsim.dev/use-cas