Connect Stockyard to every LLM platform, framework, and tool.

Stockyard integrations let you add cost caps, caching, rate limiting, PII redaction, smart routing, failover, and analytics to any platform that makes LLM API calls — without changing your application code.

Every integration follows the same pattern:

1. Stockyard runs as a proxy on localhost:4000 (or any port)
2. Your platform connects to Stockyard instead of directly to OpenAI/Anthropic
3. Stockyard forwards requests to the real LLM provider
4. Everything is automatic — cost caps, caching, rate limiting, PII redaction, analytics

[Your App] → [Stockyard Proxy :4000] → [OpenAI / Anthropic / Groq / Ollama]
                    ↓
            Cost Caps ✓
            Caching ✓
            Rate Limiting ✓
            PII Redaction ✓
            Smart Routing ✓
            Analytics ✓

# 1. Start Stockyard
OPENAI_API_KEY=sk-... npx @stockyard/stockyard

# 2. Point your platform at Stockyard
#    Base URL: http://localhost:4000/v1
#    API Key: any-non-empty-string

# 3. Open dashboard
open http://localhost:4000/ui

MIT