diff --git a/README.md b/README.md
index 66bd398..b57a654 100644
--- a/README.md
+++ b/README.md
@@ -45,14 +45,100 @@ LocalAGI ensures your data stays exactly where you want it—on your hardware. N
 git clone https://github.com/mudler/LocalAGI
 cd LocalAGI
 
-# CPU setup
-docker compose up -f docker-compose.yml
+# CPU setup (default)
+docker compose up
 
-# GPU setup
-docker compose up -f docker-compose.gpu.yml
+# NVIDIA GPU setup
+docker compose --profile nvidia up
+
+# Intel GPU setup (for Intel Arc and integrated GPUs)
+docker compose --profile intel up
+
+# Start with a specific model (see available models in models.localai.io, or localai.io to use any model in huggingface)
+MODEL_NAME=gemma-3-12b-it docker compose up
+
+# NVIDIA GPU setup with custom multimodal and image models
+MODEL_NAME=gemma-3-12b-it \
+MULTIMODAL_MODEL=minicpm-v-2_6 \
+IMAGE_MODEL=flux.1-dev \
+docker compose --profile nvidia up
 ```
 
-Access your agents at `http://localhost:8080`
+Now you can access and manage your agents at [http://localhost:8080](http://localhost:8080)
+
+## 🖥️ Hardware Configurations
+
+LocalAGI supports multiple hardware configurations through Docker Compose profiles:
+
+### CPU (Default)
+- No special configuration needed
+- Runs on any system with Docker
+- Best for testing and development
+- Supports text models only
+
+### NVIDIA GPU
+- Requires NVIDIA GPU and drivers
+- Uses CUDA for acceleration
+- Best for high-performance inference
+- Supports text, multimodal, and image generation models
+- Run with: `docker compose --profile nvidia up`
+- Default models:
+  - Text: `openthinker-7b`
+  - Multimodal: `minicpm-v-2_6`
+  - Image: `flux.1-dev`
+- Environment variables:
+  - `MODEL_NAME`: Text model to use
+  - `MULTIMODAL_MODEL`: Multimodal model to use
+  - `IMAGE_MODEL`: Image generation model to use
+  - `LOCALAI_SINGLE_ACTIVE_BACKEND`: Set to `true` to enable single active backend mode
+
+### Intel GPU
+- Supports Intel Arc and integrated GPUs
+- Uses SYCL for acceleration
+- Best for Intel-based systems
+- Supports text, multimodal, and image generation models
+- Run with: `docker compose --profile intel up`
+- Default models:
+  - Text: `openthinker-7b`
+  - Multimodal: `minicpm-v-2_6`
+  - Image: `sd-1.5-ggml`
+- Environment variables:
+  - `MODEL_NAME`: Text model to use
+  - `MULTIMODAL_MODEL`: Multimodal model to use
+  - `IMAGE_MODEL`: Image generation model to use
+  - `LOCALAI_SINGLE_ACTIVE_BACKEND`: Set to `true` to enable single active backend mode
+
+## Customize models
+
+You can customize the models used by LocalAGI by setting environment variables when running docker-compose. For example:
+
+```bash
+# CPU with custom model
+MODEL_NAME=gemma-3-12b-it docker compose up
+
+# NVIDIA GPU with custom models
+MODEL_NAME=gemma-3-12b-it \
+MULTIMODAL_MODEL=minicpm-v-2_6 \
+IMAGE_MODEL=flux.1-dev \
+docker compose --profile nvidia up
+
+# Intel GPU with custom models
+MODEL_NAME=gemma-3-12b-it \
+MULTIMODAL_MODEL=minicpm-v-2_6 \
+IMAGE_MODEL=sd-1.5-ggml \
+docker compose --profile intel up
+```
+
+If no models are specified, it will use the defaults:
+- Text model: `openthinker-7b`
+- Multimodal model: `minicpm-v-2_6`
+- Image model: `flux.1-dev` (NVIDIA) or `sd-1.5-ggml` (Intel)
+
+Good (relatively small) models that have been tested are:
+
+- `qwen_qwq-32b` (best in co-ordinating agents)
+- `gemma-3-12b-it`
+- `gemma-3-27b-it`
 
 ## 🏆 Why Choose LocalAGI?
 
@@ -98,6 +184,8 @@ Explore detailed documentation including:
 
 ### Environment Configuration
 
+LocalAGI supports environment configurations. Note that these environment variables needs to be specified in the localagi container in the docker-compose file to have effect.
+
 | Variable | What It Does |
 |----------|--------------|
 | `LOCALAGI_MODEL` | Your go-to model |
diff --git a/core/action/plan.go b/core/action/plan.go
index f1c4c5d..6f8d5b3 100644
--- a/core/action/plan.go
+++ b/core/action/plan.go
@@ -41,7 +41,7 @@ func (a *PlanAction) Plannable() bool {
 func (a *PlanAction) Definition() types.ActionDefinition {
 	return types.ActionDefinition{
 		Name:        PlanActionName,
-		Description: "Use this tool for solving complex tasks that involves calling more tools in sequence.",
+		Description: "Use it for situations that involves doing more actions in sequence.",
 		Properties: map[string]jsonschema.Definition{
 			"subtasks": {
 				Type:        jsonschema.Array,
diff --git a/core/agent/templates.go b/core/agent/templates.go
index 5f657ea..346737b 100644
--- a/core/agent/templates.go
+++ b/core/agent/templates.go
@@ -115,7 +115,7 @@ Available Tools:
 const reSelfEvalTemplate = pickSelfTemplate
 
 const pickActionTemplate = hudTemplate + `
-Your only task is to analyze the situation and determine a goal and the best tool to use, or just a final response if we have fullfilled the goal.
+Your only task is to analyze the conversation and determine a goal and the best tool to use, or just a final response if we have fullfilled the goal.
 
 Guidelines:
 1. Review the current state, what was done already and context
diff --git a/docker-compose.gpu.intel.yaml b/docker-compose.gpu.intel.yaml
deleted file mode 100644
index e447f3a..0000000
--- a/docker-compose.gpu.intel.yaml
+++ /dev/null
@@ -1,75 +0,0 @@
-services:
-  localai:
-    # See https://localai.io/basics/container/#standard-container-images for
-    # a list of available container images (or build your own with the provided Dockerfile)
-    # Available images with CUDA, ROCm, SYCL, Vulkan
-    # Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
-    # Image list (dockerhub): https://hub.docker.com/r/localai/localai
-    image: localai/localai:master-sycl-f32-ffmpeg-core
-    command: 
-    # - rombo-org_rombo-llm-v3.0-qwen-32b # minimum suggested model
-    - openthinker-7b # (smaller)
-    - granite-embedding-107m-multilingual
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
-      interval: 60s
-      timeout: 10m
-      retries: 120
-    ports:
-    - 8081:8080
-    environment:
-      - DEBUG=true
-      #- LOCALAI_API_KEY=sk-1234567890
-    volumes:
-      - ./volumes/models:/build/models:cached
-      - ./volumes/images:/tmp/generated/images
-    devices:
-      # On a system with integrated GPU and an Arc 770, this is the Arc 770
-      - /dev/dri/card1
-      - /dev/dri/renderD129
-
-  localrecall:
-    image: quay.io/mudler/localrecall:main
-    ports:
-      - 8080
-    environment:
-      - COLLECTION_DB_PATH=/db
-      - EMBEDDING_MODEL=granite-embedding-107m-multilingual
-      - FILE_ASSETS=/assets
-      - OPENAI_API_KEY=sk-1234567890
-      - OPENAI_BASE_URL=http://localai:8080
-    volumes:
-      - ./volumes/localrag/db:/db
-      - ./volumes/localrag/assets/:/assets
-
-  localrecall-healthcheck:
-    depends_on:
-      localrecall:
-        condition: service_started
-    image: busybox
-    command: ["sh", "-c", "until wget -q -O - http://localrecall:8080 > /dev/null 2>&1; do echo 'Waiting for localrecall...'; sleep 1; done; echo 'localrecall is up!'"]
-
-  localagi:
-    depends_on:
-      localai:
-        condition: service_healthy
-      localrecall-healthcheck:
-        condition: service_completed_successfully
-    build:
-      context: .
-      dockerfile: Dockerfile.webui
-    ports:
-      - 8080:3000
-    image: quay.io/mudler/localagi:master
-    environment:
-      - LOCALAGI_MODEL=openthinker-7b
-      - LOCALAGI_LLM_API_URL=http://localai:8080
-      #- LOCALAGI_LLM_API_KEY=sk-1234567890
-      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
-      - LOCALAGI_STATE_DIR=/pool
-      - LOCALAGI_TIMEOUT=5m
-      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - ./volumes/localagi/:/pool
diff --git a/docker-compose.gpu.yaml b/docker-compose.gpu.yaml
deleted file mode 100644
index 3cf67fe..0000000
--- a/docker-compose.gpu.yaml
+++ /dev/null
@@ -1,85 +0,0 @@
-services:
-  localai:
-    # See https://localai.io/basics/container/#standard-container-images for
-    # a list of available container images (or build your own with the provided Dockerfile)
-    # Available images with CUDA, ROCm, SYCL, Vulkan
-    # Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
-    # Image list (dockerhub): https://hub.docker.com/r/localai/localai
-    image: localai/localai:master-gpu-nvidia-cuda-12
-    command: 
-    - mlabonne_gemma-3-27b-it-abliterated
-    - qwen_qwq-32b
-    # Other good alternative options:
-    # - rombo-org_rombo-llm-v3.0-qwen-32b # minimum suggested model
-    # - arcee-agent
-    - granite-embedding-107m-multilingual
-    - flux.1-dev
-    - minicpm-v-2_6
-    environment:
-      # Enable if you have a single GPU which don't fit all the models
-      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
-      - DEBUG=true
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
-      interval: 10s
-      timeout: 20m
-      retries: 20
-    ports:
-    - 8081:8080
-    volumes:
-      - ./volumes/models:/build/models:cached
-      - ./volumes/images:/tmp/generated/images
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-  localrecall:
-    image: quay.io/mudler/localrecall:main
-    ports:
-      - 8080
-    environment:
-      - COLLECTION_DB_PATH=/db
-      - EMBEDDING_MODEL=granite-embedding-107m-multilingual
-      - FILE_ASSETS=/assets
-      - OPENAI_API_KEY=sk-1234567890
-      - OPENAI_BASE_URL=http://localai:8080
-    volumes:
-      - ./volumes/localrag/db:/db
-      - ./volumes/localrag/assets/:/assets
-
-  localrecall-healthcheck:
-    depends_on:
-      localrecall:
-        condition: service_started
-    image: busybox
-    command: ["sh", "-c", "until wget -q -O - http://localrecall:8080 > /dev/null 2>&1; do echo 'Waiting for localrecall...'; sleep 1; done; echo 'localrecall is up!'"]
-
-  localagi:
-    depends_on:
-      localai:
-        condition: service_healthy
-      localrecall-healthcheck:
-        condition: service_completed_successfully
-    build:
-      context: .
-      dockerfile: Dockerfile.webui
-    ports:
-      - 8080:3000
-    image: quay.io/mudler/localagi:master
-    environment:
-      - LOCALAGI_MODEL=qwen_qwq-32b
-      - LOCALAGI_LLM_API_URL=http://localai:8080
-      #- LOCALAGI_LLM_API_KEY=sk-1234567890
-      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
-      - LOCALAGI_STATE_DIR=/pool
-      - LOCALAGI_TIMEOUT=5m
-      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false
-      - LOCALAGI_MULTIMODAL_MODEL=minicpm-v-2_6
-      - LOCALAGI_IMAGE_MODEL=flux.1-dev
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    volumes:
-      - ./volumes/localagi/:/pool
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 60963ba..101ebf7 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -24,14 +24,44 @@ services:
       - ./volumes/models:/build/models:cached
       - ./volumes/images:/tmp/generated/images
 
-    # decomment the following piece if running with Nvidia GPUs
-    # deploy:
-    #   resources:
-    #     reservations:
-    #       devices:
-    #         - driver: nvidia
-    #           count: 1
-    #           capabilities: [gpu]
+  localai-nvidia:
+    profiles: ["nvidia"]
+    extends:
+      service: localai
+    environment:
+      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
+      - DEBUG=true
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    command: 
+    - ${MODEL_NAME:-openthinker-7b}
+    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
+    - ${IMAGE_MODEL:-flux.1-dev}
+    - granite-embedding-107m-multilingual
+
+  localai-intel:
+    profiles: ["intel"]
+    environment:
+      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
+      - DEBUG=true
+    extends:
+      service: localai
+    image: localai/localai:master-sycl-f32-ffmpeg-core
+    devices:
+      # On a system with integrated GPU and an Arc 770, this is the Arc 770
+      - /dev/dri/card1
+      - /dev/dri/renderD129
+    command: 
+    - ${MODEL_NAME:-openthinker-7b}
+    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
+    - ${IMAGE_MODEL:-sd-1.5-ggml}
+    - granite-embedding-107m-multilingual
+
   localrecall:
     image: quay.io/mudler/localrecall:main
     ports:
@@ -77,3 +107,31 @@ services:
       - "host.docker.internal:host-gateway"
     volumes:
       - ./volumes/localagi/:/pool
+
+  localagi-nvidia:
+    profiles: ["nvidia"]
+    extends:
+      service: localagi
+    environment:
+      - LOCALAGI_MODEL=${MODEL_NAME:-openthinker-7b}
+      - LOCALAGI_MULTIMODAL_MODEL=${MULTIMODAL_MODEL:-minicpm-v-2_6}
+      - LOCALAGI_IMAGE_MODEL=${IMAGE_MODEL:-flux.1-dev}
+      - LOCALAGI_LLM_API_URL=http://localai:8080
+      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
+      - LOCALAGI_STATE_DIR=/pool
+      - LOCALAGI_TIMEOUT=5m
+      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false
+
+  localagi-intel:
+    profiles: ["intel"]
+    extends:
+      service: localagi
+    environment:
+      - LOCALAGI_MODEL=${MODEL_NAME:-openthinker-7b}
+      - LOCALAGI_MULTIMODAL_MODEL=${MULTIMODAL_MODEL:-minicpm-v-2_6}
+      - LOCALAGI_IMAGE_MODEL=${IMAGE_MODEL:-sd-1.5-ggml}
+      - LOCALAGI_LLM_API_URL=http://localai:8080
+      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
+      - LOCALAGI_STATE_DIR=/pool
+      - LOCALAGI_TIMEOUT=5m
+      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false