Stop
starting
over.

The composable AI gateway. One env var. Infinite context.

Plug in intelligence, not just guardrails.

          -ANTHROPIC_BASE_URL=https://api.anthropic.com
          +ANTHROPIC_BASE_URL=https://api.prxy.monster
          +PRXY_PIPE=mcp-optimizer,ipc,patterns
        

How it works

Point & forget

Replace one env var. Zero code changes. Every app, every framework, every model — it just works.

It learns

Every conversation forges patterns. Outcomes are tracked. Failures retire. Good solutions reinforce.

Compounds

Patterns inject before each request. Context never resets. Your AI bill goes down over time.

Composable modules

Toggle the intelligence you need.

mcp-optimizer −90% token waste

Smart tool selection. 67k of MCP tokens become 6k. Your $200 plan stops dying after 19 minutes.
ipc infinite context

Progressive compression by age. Sessions never reset. Your AI sees everything that happened.
patterns learns over time

Forges fixes from successful conversations. Injects relevant solutions before each request.
semantic-cache 23% hit rate

Cosine-similar prompts return cached responses. Free latency. Free spend.
cost-guard hard budgets

Per-key spend ceilings. 429 before you blow past. Daily, weekly, monthly.
exact-cache free repeats

Byte-for-byte matches return instantly. TTL configurable per pipe.

vs the field

Most gateways are routers.

	prxy.monster	OpenRouter	Portkey	Helicone	LiteLLM
Multi-provider routing	YES	YES	YES	YES	YES
MCP token optimization	YES	NO	NO	NO	NO
Infinite context (compressed)	YES	NO	NO	NO	NO
Pattern learning across sessions	YES	NO	NO	NO	NO
Semantic cache	YES	NO	YES	NO	NO
Self-host (MIT)	YES	NO	NO	YES	YES
Composable modules	YES	NO	NO	NO	NO
AWS Bedrock supported	YES	YES	YES	NO	YES

Plays nice

Works with what you already use.

Same wire format as Anthropic and OpenAI. Most integrations are a single env var. Zero code change for the SDKs you already have wired up.

AI Coding Tools

30 sec Claude Code One env var. Kills the 45-min rate-limit cliff. 1 setting Cursor Custom OpenAI Base URL field. 2 fields Cline OpenAI Compatible provider settings. 2 flags Aider --openai-api-base + --openai-api-key. 1 line Continue.dev apiBase in ~/.continue/config.json.

SDKs

1 env var Anthropic SDK ANTHROPIC_BASE_URL. Zero code change. 1 env var OpenAI SDK OPENAI_BASE_URL. Zero code change. 1 env var Vercel AI SDK @ai-sdk/openai + @ai-sdk/anthropic. 1 line Google GenAI @google/genai via OpenAI-compat.

Frameworks

1 arg LangChain JS configuration.baseURL on ChatOpenAI. 1 arg LangChain Python base_url on ChatOpenAI / ChatAnthropic. 1 arg LlamaIndex api_base / additionalSessionOptions.baseURL. 1 env var Mastra Inherits from the AI SDK provider config. 1 line Instructor Wraps OpenAI/Anthropic — same swap. 0 changes AI Elements UI components inherit from AI SDK config.

All integration guides →

Deploy

Cloud or local. Same modules.

Cloud

api.prxy.monster

Hosted gateway. Zero ops. Pay-as-you-go credits.

Postgres + Upstash Redis + R2 backed
Auto-scaling on Cloud Run
Patterns + cache shared across your team
Stripe billing, dashboards, BYOK supported

Local

prxy-local

Single binary. SQLite + filesystem. MIT licensed.

Runs on your laptop, your homelab, your VPS
No telemetry. Patterns stay on your machine.
Same composable modules as cloud
BYOK to whichever providers you trust

Self-deploy

AWS CDK

One-command deploy to your AWS account. Bedrock-native.

App Runner + Aurora Serverless v2 + ElastiCache + S3
Bedrock provider out of the box (Claude, Llama, Titan, Mistral, Cohere)
Your data stays in your AWS account
npm run deploy --context domain=prxy.example.com

Get
early
access.

✓ You're on the list. We'll be in touch.

Something went wrong. Try again or email hello@prxy.monster.