fix: drop 'OpenAI-compatible' from tagline, clarify it's the API format not the limitation

Author: Das-rebel

README.md

@@ -1,10 +1,10 @@
 # A3M Router
 
-**OpenAI-compatible LLM routing gateway — routes requests to the cheapest capable provider per query.**
+**Universal LLM routing gateway — routes requests to the cheapest capable provider across 47+ models.**
 
-A3M Router is a stateless proxy that sits between your application and 47+ LLM providers. It inspects each request, estimates how complex it is, and routes it to the cheapest provider that can handle it — without retraining a model or managing GPU infrastructure.
+A3M Router is a stateless proxy between your application and 47+ LLM providers. It inspects each request, estimates how complex it is, and routes it to the cheapest capable provider — without retraining a model or managing GPU infrastructure.
 
-Drop-in replacement for OpenAI API calls. Switch providers or add new ones without changing application code.
+The API uses the OpenAI format (same endpoints, same request/response shapes), so existing SDKs and prompts work without changes. But it routes across any provider you configure, not just OpenAI.
 
 ---
 
@@ -89,6 +89,9 @@ const result = await executeEnsemble(
 
 A3M is a routing engine. LiteLLM is an enterprise platform. Use the right tool for your stage.
 
+### OpenAI-Compatible API
+The API format is OpenAI-compatible — same `/v1/chat/completions` endpoints, same request/response shapes — so any OpenAI-compatible SDK or proxy tool works with A3M without code changes. This is useful for switching providers behind an existing integration or for tooling that only supports the OpenAI format.
+
 ---
 
 ## Architecture

package.json

@@ -1,9 +1,9 @@
 {
   "name": "adaptive-memory-multi-model-router",
-  "version": "2.15.0",
+  "version": "2.15.1",
   "shortName": "A3M Router",
   "displayName": "A3M Router - Adaptive Memory Multi-Model Router",
-  "description": "OpenAI-compatible LLM routing gateway. Routes requests to cheapest capable provider across 47+ providers. Heuristic routing, parallel ensemble, semantic cache. Drop-in for OpenAI SDK.",
+  "description": "Universal LLM routing gateway. Routes requests to cheapest capable provider across 47+ models. Heuristic routing, parallel ensemble, semantic cache.",
   "main": "dist/index.js",
   "bin": {
     "a3m-router": "dist/cli.js",