circuit-breaker-sage.vercel.app is built with Next.js, hosted on AWS. It measures traffic with Vercel Web Analytics.
| Technology | Version | First seen |
|---|---|---|
| JavaScript Frameworks & Libraries2 | ||
| 16.3.8 | 6 Nov 2026 | |
| – | 6 Nov 2026 | |
| Frontend Build Tools & CSS2 | ||
| – | 6 Nov 2026 | |
| Web Servers, Languages & Backend Frameworks1 | ||
| CDN & Hosting2 | ||
| – | 6 Nov 2026 | |
| Analytics & Tag Management1 | ||
| – | 6 Nov 2026 | |
| Fonts & Icon Fonts2 | ||
| – | 6 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
User-Agent: * Allow: / Sitemap: https://circuit-breaker-sage.vercel.app/sitemap.xml
# Shunt
> The In-Memory LLM Firewall.
Shunt intercepts chat completion calls to upstream providers (OpenAI, Anthropic), detects recursive agent error loops using a sliding-window SHA-256 hash deque, and stops runaway streams before budget exhaustion.
## Quickstart Drop-in
- Base URL: https://circuit-breaker-api.onrender.com/v1
- Upstream Compatibility: 100% OpenAI /v1/chat/completions compatible.
- Latency Overhead: <35ms.
- Streaming: Unbuffered Server-Sent Events (SSE).
## Integration Example (Python)
```python
from openai import OpenAI
client = OpenAI(
base_url="https://circuit-breaker-api.onrender.com/v1",
api_key="cb_live_your_proxy_key"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Execute agent task..."}],
stream=True
)| – |
| 6 Nov 2026 |
| – |
| 6 Nov 2026 |
| – |
| 6 Nov 2026 |
| – |
| 6 Nov 2026 |