update demo docs and comments to reflect native-first approach

Author: adilhafeez

config/test_passthrough.yaml

@@ -6,8 +6,8 @@
 # that manage their own API key validation.
 #
 # To test:
-#   docker build -t plano-passthrough-test .
-#   docker run -d -p 10000:10000 -v $(pwd)/config/test_passthrough.yaml:/app/plano_config.yaml plano-passthrough-test
+#   pip install planoai
+#   planoai up config/test_passthrough.yaml
 #
 #   curl http://localhost:10000/v1/chat/completions \
 #     -H "Authorization: Bearer sk-your-virtual-key" \

demos/agent_orchestration/multi_agent_crewai_langchain/README.md

@@ -38,18 +38,17 @@ Plano acts as a **framework-agnostic proxy and data plane** that:
 ```bash
 # From the demo directory
 cd demos/agent_orchestration/multi_agent_crewai_langchain
-
-# Build and start all services
-docker-compose up -d
+./run_demo.sh
 ```
 
-This starts:
-- **Plano** (ports 12000, 8001) - routing and orchestration
+This starts Plano natively and brings up via Docker Compose:
 - **CrewAI Flight Agent** (port 10520) - flight search
 - **LangChain Weather Agent** (port 10510) - weather forecasts
 - **AnythingLLM** (port 3001) - chat interface
 - **Jaeger** (port 16686) - distributed tracing
 
+Plano runs natively on the host (ports 12000, 8001).
+
 ### Try It Out
 
 1. **Open the Chat Interface**
@@ -116,7 +115,7 @@ This starts:
 ## Cleanup
 
 ```bash
-docker-compose down
+./run_demo.sh down
 ```
 
 ## Next Steps

demos/agent_orchestration/travel_agents/README.md

@@ -9,7 +9,7 @@ This demo consists of two intelligent agents that work together seamlessly:
 - **Weather Agent** - Real-time weather conditions and multi-day forecasts for any city worldwide
 - **Flight Agent** - Live flight information between airports with real-time tracking
 
-All agents use Plano's agent orchestration LLM to intelligently route user requests to the appropriate specialized agent based on conversation context and user intent. Both agents run as Docker containers for easy deployment.
+All agents use Plano's agent orchestration LLM to intelligently route user requests to the appropriate specialized agent based on conversation context and user intent.
 
 ## Features
 
@@ -22,8 +22,8 @@ All agents use Plano's agent orchestration LLM to intelligently route user reque
 
 ## Prerequisites
 
-- Docker and Docker Compose
-- [Plano CLI](https://docs.planoai.dev/get_started/quickstart.html#prerequisites) installed
+- [Plano CLI](https://docs.planoai.dev/get_started/quickstart.html#prerequisites) installed (`pip install planoai`)
+- Docker and Docker Compose (for agent services)
 - [OpenAI API key](https://platform.openai.com/api-keys)
 - [FlightAware AeroAPI key](https://www.flightaware.com/aeroapi/portal)
 
@@ -40,17 +40,18 @@ export AEROAPI_KEY="your-flightaware-api-key"
 export OPENAI_API_KEY="your OpenAI api key"
 ```
 
-### 2. Start All Agents & Plano with Docker
+### 2. Start the Demo
 
 ```bash
-docker compose up --build
+./run_demo.sh
 ```
 
-This starts:
+This starts Plano natively and brings up via Docker Compose:
 - Weather Agent on port 10510
 - Flight Agent on port 10520
 - Open WebUI on port 8080
-- Plano Proxy on port 8001
+
+Plano runs natively on the host (port 8001).
 
 ### 4. Test the System
 
@@ -92,7 +93,7 @@ Assistant: [Both weather_agent and flight_agent respond simultaneously]
  Weather     Flight
   Agent       Agent
  (10510)     (10520)
- [Docker]    [Docker]
+ (10510)     (10520)
 ```
 
 Each agent:
@@ -101,7 +102,7 @@ Each agent:
 3. Generates response using GPT-5.2
 4. Streams response back to user
 
-Both agents run as Docker containers and communicate with Plano via `host.docker.internal`.
+Both agents run as Docker containers and communicate with Plano running natively on the host.
 
 ## Observability
 

demos/filter_chains/http_filter/README.md

@@ -35,21 +35,21 @@ This demo consists of four components:
 
 ## Quick Start
 
-### 1. Start everything with Docker Compose
+### 1. Start the demo
 ```bash
-docker compose up --build
+export OPENAI_API_KEY="your-key"
+./run_demo.sh
 ```
 
-This brings up:
+This starts Plano natively and brings up via Docker Compose:
 - Input Guards MCP server on port 10500
 - Query Rewriter MCP server on port 10501
 - Context Builder MCP server on port 10502
 - RAG Agent REST server on port 10505
-- Plano listener on port 8001 (and gateway on 12000)
 - Jaeger UI for viewing traces at http://localhost:16686
 - AnythingLLM at http://localhost:3001 for interactive queries
 
-> Set `OPENAI_API_KEY` in your environment before running; `LLM_GATEWAY_ENDPOINT` defaults to `http://host.docker.internal:12000/v1`.
+Plano runs natively on the host (port 8001 and 12000).
 
 ### 2. Test the system
 

demos/filter_chains/mcp_filter/README.md

@@ -35,21 +35,21 @@ This demo consists of four components:
 
 ## Quick Start
 
-### 1. Start everything with Docker Compose
+### 1. Start the demo
 ```bash
-docker compose up --build
+export OPENAI_API_KEY="your-key"
+./run_demo.sh
 ```
 
-This brings up:
+This starts Plano natively and brings up via Docker Compose:
 - Input Guards MCP server on port 10500
 - Query Rewriter MCP server on port 10501
 - Context Builder MCP server on port 10502
 - RAG Agent REST server on port 10505
-- Plano listener on port 8001 (and gateway on 12000)
 - Jaeger UI for viewing traces at http://localhost:16686
 - AnythingLLM at http://localhost:3001 for interactive queries
 
-> Set `OPENAI_API_KEY` in your environment before running; `LLM_GATEWAY_ENDPOINT` defaults to `http://host.docker.internal:12000/v1`.
+Plano runs natively on the host (port 8001 and 12000).
 
 ### 2. Test the system
 

demos/llm_routing/claude_code_router/README.md

@@ -39,8 +39,8 @@ Your Request → Plano → Suitable Model → Response
 # Install Claude Code if you haven't already
 npm install -g @anthropic-ai/claude-code
 
-# Ensure Docker is running
-docker --version
+# Install Plano CLI
+pip install planoai
 ```
 
 ### Step 1: Get Configuration

demos/llm_routing/openclaw_routing/README.md

@@ -23,7 +23,6 @@ Plano uses a [preference-aligned router](https://arxiv.org/abs/2506.16655) to an
 
 ## Prerequisites
 
-- **Docker** running
 - **Plano CLI**: `uv tool install planoai` or `pip install planoai`
 - **OpenClaw**: `npm install -g openclaw@latest`
 - **API keys**:
@@ -43,7 +42,7 @@ export ANTHROPIC_API_KEY="your-anthropic-key"
 
 ```bash
 cd demos/llm_routing/openclaw_routing
-planoai up --service plano --foreground
+planoai up config.yaml
 ```
 
 ### 3. Set Up OpenClaw

demos/llm_routing/preference_based_routing/README.md

@@ -3,25 +3,23 @@ This demo shows how you can use user preferences to route user prompts to approp
 
 ## How to start the demo
 
-Make sure your machine is up to date with [latest version of plano]([url](https://github.com/katanemo/plano/tree/main?tab=readme-ov-file#prerequisites)). And you have activated the virtual environment.
+Make sure you have Plano CLI installed (`pip install planoai` or `uv tool install planoai`).
 
+```bash
+cd demos/llm_routing/preference_based_routing
+./run_demo.sh
+```
+
+Or manually:
 
-1. start anythingllm
+1. Start Plano
 ```bash
-(venv) $ cd demos/llm_routing/preference_based_routing
-(venv) $ docker compose up -d
+planoai up config.yaml
 ```
-2. start plano in the foreground
+
+2. Start AnythingLLM
 ```bash
-(venv) $ planoai up --service plano --foreground
-# Or if installed with uv: uvx planoai up --service plano --foreground
-2025-05-30 18:00:09,953 - planoai.main - INFO - Starting plano cli version: 0.4.9
-2025-05-30 18:00:09,953 - planoai.main - INFO - Validating /Users/adilhafeez/src/intelligent-prompt-gateway/demos/llm_routing/preference_based_routing/config.yaml
-2025-05-30 18:00:10,422 - cli.core - INFO - Starting plano gateway, image name: plano, tag: katanemo/plano:0.4.9
-2025-05-30 18:00:10,662 - cli.core - INFO - plano status: running, health status: starting
-2025-05-30 18:00:11,712 - cli.core - INFO - plano status: running, health status: starting
-2025-05-30 18:00:12,761 - cli.core - INFO - plano is running and is healthy!
-...
+docker compose up -d
 ```
 
 3. open AnythingLLM http://localhost:3001/