@opensearch-project/agent-health 0.3.0 → 0.4.0

package/README.md

@@ -80,12 +80,23 @@ Get Agent Health running in minutes. Choose the option that best suits your need
 npx @opensearch-project/agent-health
 ```
 
-Opens http://localhost:4001 with pre-loaded sample data for exploration.
+Opens http://localhost:4001 with pre-loaded sample data for exploration. If port 4001 is already in use, the server automatically tries the next available port (4002, 4003, etc., up to 10 attempts).
 
 ### Option 2: Docker Compose (with OpenSearch Observability Stack)
 
 For the full observability stack with OpenSearch, OpenTelemetry Collector, and Data Prepper for trace ingestion:
 
+**Quick start (one command):**
+
+```bash
+curl -fsSL https://raw.githubusercontent.com/opensearch-project/agent-health/main/scripts/install.sh | bash
+```
+
+This clones the repo, starts the Docker stack, waits for OpenSearch, auto-configures `agent-health.config.json`, and launches Agent Health.
+
+<details>
+<summary><b>Or step-by-step:</b></summary>
+
 ```bash
 # Clone the repository
 git clone https://github.com/opensearch-project/agent-health.git
@@ -100,6 +111,7 @@ cp .env.docker .env
 # Start Agent Health (connects to local OpenSearch automatically)
 npx @opensearch-project/agent-health
 ```
+</details>
 
 This brings up:
 - **OpenSearch** — Stores traces, test cases, benchmarks, and evaluation results
@@ -108,6 +120,30 @@ This brings up:
 
 > **Prerequisites:** Docker Desktop with 4GB+ memory allocated. See [docker-compose.yml](./docker-compose.yml) for configuration options.
 
+### Option 3: AWS CloudFormation (Managed OpenSearch)
+
+Deploy a fully managed observability backend using the included CloudFormation template:
+
+```bash
+aws cloudformation create-stack \
+  --stack-name AgentHealthObservability \
+  --template-body file://deployment/cloudformation/agent-health-observability.yaml \
+  --capabilities CAPABILITY_NAMED_IAM
+```
+
+This deploys:
+- **Amazon OpenSearch Service** domain for trace storage
+- **OpenSearch Ingestion (OSIS)** pipeline for OTLP data collection
+- **IAM roles** for pipeline execution and agent telemetry ingestion
+
+After deployment, connect it to Agent Health:
+
+```bash
+npx @opensearch-project/agent-health configure --from-stack AgentHealthObservability
+```
+
+Or manually copy the `AgentHealthConfigJSON` stack output into your `agent-health.config.json`. See [deployment/cloudformation/](./deployment/cloudformation/) for details and regional Launch Stack URLs.
+
 ### Next Steps
 
 - [Getting Started Guide](./GETTING_STARTED.md) — Step-by-step walkthrough from install to first evaluation
@@ -150,6 +186,9 @@ A unified dashboard for monitoring AI coding agent usage across **Claude Code**,
 |-----------|----------|-------------|
 | `agui-streaming` | AG-UI SSE | ML-Commons agents (default) |
 | `rest` | HTTP POST | Non-streaming REST APIs |
+| `openai-compatible` | OpenAI Chat | LiteLLM, Ollama, vLLM |
+| `strands` | Bedrock Agent Runtime | Amazon Strands agents (server-only) |
+| `langgraph` | LangGraph REST | Non-AG-UI LangGraph instances |
 | `subprocess` | CLI | Command-line tools |
 | `claude-code` | Claude CLI | Claude Code agent comparison |
 | `mock` | In-memory | Demo and testing |
@@ -200,7 +239,7 @@ export default {
       key: "my-agent",
       name: "My Agent",
       endpoint: "http://localhost:8000/agent",
-      connectorType: "rest",  // or "agui-streaming", "subprocess"
+      connectorType: "rest",  // or "agui-streaming", "langgraph", "strands", "subprocess"
       models: ["claude-sonnet-4"],
       useTraces: true,        // Enable OpenTelemetry trace collection
     }
@@ -243,6 +282,8 @@ npm run dev          # Frontend on port 4000
 npm run dev:server   # Backend on port 4001
 ```
 
+> **Port conflicts:** If port 4001 is already in use, the backend server automatically tries 4002, 4003, etc. (up to 10 attempts). The actual port is displayed in the console output.
+
 All commits require DCO signoff (`git commit -s`) and all PRs must pass CI checks.
 
 For detailed development setup, testing, CI pipeline, debugging, and troubleshooting, see the [Developer Guide](./DEVELOPER_GUIDE.md). For full contribution guidelines, see [CONTRIBUTING.md](./CONTRIBUTING.md).