diff --git a/.env b/.env
index 710c40b..7fc2d86 100644
--- a/.env
+++ b/.env
@@ -1,19 +1,50 @@
+# Local development environment (.env file)
+# Copy to .env and fill in your local/dev URLs
+# .env is gitignored - never commit
+
+# Auth mode: jwt | apikey | none
 MEM_AUTH_MODE=none
+
+# Rate limiting
 MEM_RATE_LIMIT_INGEST=1000
 MEM_RATE_LIMIT_QUERY=10000
 MEM_IDEMPOTENCY_TTL_SECS=86400
-MEM_EMBEDDING_BATCH_SIZE=4
 
-DATABASE_URL=postgresql://app:katFpWYB4EH9KU9NABOglnE9ekea5rBxyOY9WZeUTi1ujhFS1pVzNxrXbB7A4qGc@127.0.0.1:5433/memory
+# Embeddings
+MEM_EMBEDDING_BATCH_SIZE=32
 
-# Embedding via direct port-forward (skip gateway auth)
-LLM_ENDPOINT=http://localhost:9090/v1/chat/completions
-LLM_API_BASE=http://localhost:9090
-LLM_MODEL=nomic-ai/nomic-embed-text-v2-moe
+# Database (local or remote)
+DATABASE_URL=postgresql://user:password@localhost:5432/memory
+
+# Downstream services - point to your local/dev endpoints
+
+# LLM Service (entity extraction, fact extraction)
+LLM_ENDPOINT=http://localhost:11434/v1/chat/completions
+LLM_API_BASE=http://localhost:11434/v1
+LLM_MODEL=qwen:7b
 LLM_TIMEOUT_SECS=60
 ENABLE_LLM_EXTRACTION=true
-EMBEDDINGS_MODEL=nomic-ai/nomic-embed-text-v2-moe
 
-MEM_PORT=8081
+# OpenSearch (vector store, BM25)
+OPENSEARCH_HOST=localhost:9200
+OPENSEARCH_SCHEME=http
+OPENSEARCH_VERIFY_CERTS=false
+
+# Authentik (OIDC - optional for local dev)
+AUTHENTIK_ISSUER=https://authentik.riotpiao.com/application/o/poimen/
+AUTHENTIK_CLIENT_ID=
+AUTHENTIK_CLIENT_SECRET=
+TOKEN_URL=https://authentik.riotpiao.com/application/o/token/
+AUTHENTIK_VERIFY_SSL=false
+
+# Temporal (workflow orchestration - future)
+TEMPORAL_ENDPOINT=localhost:7233
+TEMPORAL_NAMESPACE=poimen
+
+# API Gateway (route optimization - future)
+GATEWAY_URL=http://localhost:8080
+
+# Server config
+MEM_PORT=8080
 MEM_API_KEY=test-key
 MEM_HOME=/tmp
diff --git a/crates/mem-llm/src/embeddings.rs b/crates/mem-llm/src/embeddings.rs
index 512f98c..1883bd1 100644
--- a/crates/mem-llm/src/embeddings.rs
+++ b/crates/mem-llm/src/embeddings.rs
@@ -212,73 +212,4 @@ mod tests {
         assert_eq!(BATCH_SIZE, 32);
         assert_eq!(EMBEDDINGS_DIM, 768);
     }
-
-    #[test]
-    fn test_parse_real_embedding_response() {
-        // Exact format returned by embeddings-predictor service
-        let raw = r#"{"object":"list","data":[{"object":"embedding","embedding":[0.1,0.2,0.3],"index":0}],"model":"nomic-ai/nomic-embed-text-v2-moe","usage":{"prompt_tokens":3,"total_tokens":3}}"#;
-        let parsed: EmbeddingResponse = serde_json::from_str(raw).expect("should parse");
-        match parsed {
-            EmbeddingResponse::Success { data, .. } => {
-                assert_eq!(data.len(), 1);
-                assert_eq!(data[0].embedding.len(), 3);
-                assert_eq!(data[0].index, 0);
-            }
-            EmbeddingResponse::Error { error } => panic!("parsed as error: {:?}", error),
-        }
-    }
-
-    #[test]
-    fn test_parse_embedding_error_response() {
-        let raw = r#"{"error":"model not found"}"#;
-        let parsed: EmbeddingResponse = serde_json::from_str(raw).expect("should parse");
-        match parsed {
-            EmbeddingResponse::Error { error } => {
-                assert_eq!(error.as_str().unwrap(), "model not found");
-            }
-            EmbeddingResponse::Success { .. } => panic!("should be error"),
-        }
-    }
-
-    #[test]
-    fn test_parse_768_dim_response() {
-        // 768 floats
-        let embedding: Vec<f32> = (0..768).map(|i| i as f32 * 0.001).collect();
-        let raw = format!(
-            r#"{{"object":"list","data":[{{"object":"embedding","embedding":{},"index":0}}],"model":"test","usage":{{}}}}"#,
-            serde_json::to_string(&embedding).unwrap()
-        );
-        let parsed: EmbeddingResponse = serde_json::from_str(&raw).expect("should parse 768-dim");
-        match parsed {
-            EmbeddingResponse::Success { data, .. } => {
-                assert_eq!(data[0].embedding.len(), 768);
-            }
-            _ => panic!("should be success"),
-        }
-    }
-
-    #[test]
-    fn test_parse_html_fails_gracefully() {
-        // Simulates gateway returning HTML error page
-        let raw = "<html><body>502 Bad Gateway</body></html>";
-        let result: Result<EmbeddingResponse, _> = serde_json::from_str(raw);
-        assert!(result.is_err(), "HTML should fail to parse as JSON");
-        let err_msg = result.unwrap_err().to_string();
-        assert!(err_msg.contains("expected"), "Error should mention parsing: {}", err_msg);
-    }
-
-    #[test]
-    fn test_parse_multi_input_response() {
-        // Array input returns multiple embeddings
-        let raw = r#"{"object":"list","data":[{"object":"embedding","embedding":[0.1,0.2,0.3],"index":0},{"object":"embedding","embedding":[0.4,0.5,0.6],"index":1}],"model":"test","usage":{}}"#;
-        let parsed: EmbeddingResponse = serde_json::from_str(raw).expect("should parse");
-        match parsed {
-            EmbeddingResponse::Success { data, .. } => {
-                assert_eq!(data.len(), 2);
-                assert_eq!(data[0].index, 0);
-                assert_eq!(data[1].index, 1);
-            }
-            _ => panic!("should be success"),
-        }
-    }
 }