diff --git a/.env.example b/.env.example
index 7be4ee38..d78e89ab 100644
--- a/.env.example
+++ b/.env.example
@@ -1,85 +1,7 @@
-# Hindsight Environment Variables
-# Copy this file to .env and fill in your values
+# Required: LLM provider for memory classification
+LLM_API_KEY=sk-your-key-here
+LLM_PROVIDER=openai
+LLM_MODEL=gpt-4o-mini
 
-# LLM Configuration (Required)
-# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, volcano
-HINDSIGHT_API_LLM_PROVIDER=openai
-HINDSIGHT_API_LLM_API_KEY=your-api-key-here
-HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
-HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
-
-# Example: Anthropic Claude configuration
-# HINDSIGHT_API_LLM_PROVIDER=anthropic
-# HINDSIGHT_API_LLM_API_KEY=your-anthropic-api-key
-# HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-20250514
-
-# Example: Google Vertex AI configuration
-# HINDSIGHT_API_LLM_PROVIDER=vertexai
-# HINDSIGHT_API_LLM_MODEL=google/gemini-2.0-flash-001
-# HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID=your-gcp-project-id
-# HINDSIGHT_API_LLM_VERTEXAI_REGION=us-central1
-# HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY=/path/to/service-account-key.json  # Optional, uses ADC if not set
-
-# Example: MiniMax configuration (1M context window)
-# HINDSIGHT_API_LLM_PROVIDER=minimax
-# HINDSIGHT_API_LLM_API_KEY=your-minimax-api-key
-# HINDSIGHT_API_LLM_MODEL=MiniMax-M2.7
-
-# Example: LM Studio local configuration (Qwen 2.5 32B recommended)
-# HINDSIGHT_API_LLM_PROVIDER=lmstudio
-# HINDSIGHT_API_LLM_API_KEY=lmstudio
-# HINDSIGHT_API_LLM_BASE_URL=http://localhost:1234/v1
-# HINDSIGHT_API_LLM_MODEL=qwen2.5-32b-instruct
-
-# API Configuration (Optional)
-HINDSIGHT_API_HOST=0.0.0.0
-HINDSIGHT_API_PORT=8888
-HINDSIGHT_API_LOG_LEVEL=info
-
-# Base Path / Reverse Proxy Support (Optional)
-# Set these when deploying behind a reverse proxy with path-based routing
-# Example: To deploy at example.com/hindsight/, set both to "/hindsight"
-# HINDSIGHT_API_BASE_PATH=/hindsight
-# NEXT_PUBLIC_BASE_PATH=/hindsight
-
-# Database (Optional - uses embedded pg0 by default)
-# HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@host:5432/db
-# HINDSIGHT_API_MIGRATION_DATABASE_URL=  # Direct PostgreSQL URL for migrations (bypasses PgBouncer). Falls back to DATABASE_URL.
-# HINDSIGHT_API_DATABASE_SCHEMA=public  # PostgreSQL schema name (default: public)
-
-# Vector Extension (Optional - uses pgvector by default)
-# Options: "pgvector" (default), "vchord", "pgvectorscale" (DiskANN)
-# HINDSIGHT_API_VECTOR_EXTENSION=pgvector
-# For Azure PostgreSQL with DiskANN:
-# HINDSIGHT_API_VECTOR_EXTENSION=pgvectorscale  # Auto-detects pg_diskann on Azure
-
-# Embeddings Configuration (Optional - uses local by default)
-# Provider: "local" (default) or "tei" (HuggingFace Text Embeddings Inference)
-# HINDSIGHT_API_EMBEDDINGS_PROVIDER=local
-# For local provider:
-# HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-small-en-v1.5
-# For TEI provider:
-# HINDSIGHT_API_EMBEDDINGS_TEI_URL=http://localhost:8080
-
-# Reranker Configuration (Optional - uses local by default)
-# Provider: "local" (default) or "tei" (HuggingFace Text Embeddings Inference)
-# HINDSIGHT_API_RERANKER_PROVIDER=local
-# For local provider:
-# HINDSIGHT_API_RERANKER_LOCAL_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
-# For TEI provider:
-# HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081
-
-# Observability & Tracing (Optional - disabled by default)
-# Enable OpenTelemetry tracing for LLM calls (GenAI semantic conventions)
-# HINDSIGHT_API_OTEL_TRACES_ENABLED=true
-#
-# Local development with Grafana LGTM stack (recommended - see scripts/dev/grafana/README.md)
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318
-#
-# Cloud backends (Grafana Cloud, Langfuse, DataDog, etc.)
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_ENDPOINT=https://your-backend-url
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer your-token"
-#
-# Custom service name and environment (optional, defaults: hindsight-api, development)
-# HINDSIGHT_API_OTEL_SERVICE_NAME=hindsight-production
-# HINDSIGHT_API_OTEL_DEPLOYMENT_ENVIRONMENT=production
+# Optional: database password (default: hindsight_dev)
+DB_PASSWORD=hindsight_dev
diff --git a/docker-compose.rcll.yml b/docker-compose.rcll.yml
new file mode 100644
index 00000000..fb5d582b
--- /dev/null
+++ b/docker-compose.rcll.yml
@@ -0,0 +1,50 @@
+version: "3.8"
+
+# RCLL — local dev stack (API + pgvector).
+# Note: the HINDSIGHT_API_* variables below are upstream config names and stay
+# as-is on purpose — we rebrand the product, not the config interface.
+
+services:
+  db:
+    image: pgvector/pgvector:pg16
+    environment:
+      POSTGRES_DB: hindsight
+      POSTGRES_USER: hindsight
+      POSTGRES_PASSWORD: ${DB_PASSWORD:-hindsight_dev}
+    volumes:
+      - hindsight_data:/var/lib/postgresql/data
+    ports:
+      - "5432:5432"
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U hindsight"]
+      interval: 5s
+      timeout: 5s
+      retries: 5
+
+  rcll:
+    build:
+      context: ./hindsight-api-slim
+      dockerfile: Dockerfile
+    depends_on:
+      db:
+        condition: service_healthy
+    environment:
+      HINDSIGHT_API_DATABASE_URL: postgresql://hindsight:${DB_PASSWORD:-hindsight_dev}@db:5432/hindsight
+      HINDSIGHT_API_MIGRATION_DATABASE_URL: postgresql+psycopg2://hindsight:${DB_PASSWORD:-hindsight_dev}@db:5432/hindsight
+      HINDSIGHT_API_HOST: "0.0.0.0"
+      HINDSIGHT_API_PORT: "5100"
+      HINDSIGHT_API_LOG_LEVEL: info
+      HINDSIGHT_API_LLM_PROVIDER: ${LLM_PROVIDER:-openai}
+      HINDSIGHT_API_LLM_API_KEY: ${LLM_API_KEY}
+      HINDSIGHT_API_LLM_MODEL: ${LLM_MODEL:-gpt-4o-mini}
+      HINDSIGHT_API_EMBEDDINGS_PROVIDER: local
+      HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU: "true"
+      HINDSIGHT_API_RERANKER_PROVIDER: local
+      HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU: "true"
+      HINDSIGHT_API_RUN_MIGRATIONS: "true"
+      HINDSIGHT_API_WORKERS: "1"
+    ports:
+      - "5100:5100"
+
+volumes:
+  hindsight_data:
diff --git a/docker/standalone/start-all.sh b/docker/standalone/start-all.sh
index b5f163e6..007d7d89 100755
--- a/docker/standalone/start-all.sh
+++ b/docker/standalone/start-all.sh
@@ -156,7 +156,10 @@ PIDS=()
 # Start API if enabled
 if [ "$ENABLE_API" = "true" ]; then
     cd /app/api
-    API_HEALTH_URL="${HINDSIGHT_API_HEALTH_URL:-http://localhost:8888/health}"
+    # Health probe must follow HINDSIGHT_API_PORT — hardcoding 8888 made the
+    # readiness check hit a dead port whenever the API was bound elsewhere,
+    # timing out after API_STARTUP_WAIT_SECONDS and exiting 1 → crash loop.
+    API_HEALTH_URL="${HINDSIGHT_API_HEALTH_URL:-http://localhost:${HINDSIGHT_API_PORT:-8888}/health}"
     API_STARTUP_WAIT_SECONDS="${HINDSIGHT_API_STARTUP_WAIT_SECONDS:-300}"
 
     # Run API directly - Python's PYTHONUNBUFFERED=1 handles output buffering
@@ -207,7 +210,7 @@ if [ "$ENABLE_CP" = "true" ]; then
     echo "   Control Plane: http://localhost:${HINDSIGHT_CP_PORT:-9999}"
 fi
 if [ "$ENABLE_API" = "true" ]; then
-    echo "   API:           http://localhost:8888"
+    echo "   API:           http://localhost:${HINDSIGHT_API_PORT:-8888}"
 fi
 echo ""