updated links, moved examples into basic folder

Author: steven10a

README.md

@@ -9,7 +9,7 @@ Clone the repository and install locally:
 
 ```bash
 # Clone the repository
-git clone https://github.com/openai/guardrails-js.git
+git clone https://github.com/openai/openai-guardrails-js.git
 cd guardrails-js
 
 # Install dependencies
@@ -134,7 +134,7 @@ await eval.run('Evaluating my dataset');
 
 ## Examples
 
-The package includes comprehensive examples in the `examples/` directory:
+The package includes comprehensive examples in the [`examples/` directory](https://github.com/openai/openai-guardrails-js/tree/main/examples):
 
 - **`agents_sdk.ts`**: Agents SDK integration with GuardrailAgent
 - **`hello_world.ts`**: Basic chatbot with guardrails using GuardrailsOpenAI
@@ -160,37 +160,28 @@ npm run build
 
 **Using tsx (Recommended)**
 ```bash
-cd examples
-npx tsx agents_sdk.ts                    # Agents SDK integration
+cd examples/basic
 npx tsx hello_world.ts                   # Basic chatbot with guardrails
-npx tsx azure_example.ts                 # Azure OpenAI integration
-npx tsx local_model.ts                   # Local model usage
-npx tsx streaming.ts                     # Streaming responses
-npx tsx suppress_tripwire.ts             # Handling violations
 ```
 
 ## Available Guardrails
 
 The TypeScript implementation includes the following built-in guardrails:
 
-- **Keywords**: Filters content based on keyword matching
 - **Moderation**: Content moderation using OpenAI's moderation API
-- **URLs**: URL filtering and domain allowlist/blocklist
-- **PII**: Personally Identifiable Information detection
-- **NSFW**: Not Safe For Work content detection
+- **URL Filter**: URL filtering and domain allowlist/blocklist
+- **Contains PII**: Personally Identifiable Information detection
 - **Hallucination Detection**: Detects hallucinated content using vector stores
 - **Jailbreak**: Detects jailbreak attempts
-- **Competitors**: Detects mentions of competitor products
-- **Secret Keys**: Detects exposed API keys and secrets
-- **Topical Alignment**: Ensures responses stay within business scope
-- **User-Defined LLM**: Custom LLM-based guardrails
+- **Off Topic Prompts**: Ensures responses stay within business scope
+- **Custom Prompt Check**: Custom LLM-based guardrails
 
 ## License
 
 MIT License - see LICENSE file for details.
 
 ## Disclaimers
 
-Please note that Guardrails may use Third-Party Services such as the [Presidio open-source framework](https://github.com/microsoft/presidio), which are subject to their own terms and conditions and are not developed or verified by OpenAI.
+Please note that Guardrails may use Third-Party Services such as the [Presidio open-source framework](https://github.com/microsoft/presidio), which are subject to their own terms and conditions and are not developed or verified by OpenAI.  For more information on configuring guardrails, please visit: [guardrails.openai.com](https://guardrails.openai.com/)
 
 Developers are responsible for implementing appropriate safeguards to prevent storage or misuse of sensitive or prohibited content (including but not limited to personal data, child sexual abuse material, or other illegal content). OpenAI disclaims liability for any logging or retention of such content by developers. Developers must ensure their systems comply with all applicable data protection and content safety laws, and should avoid persisting any blocked content generated or intercepted by Guardrails.

docs/agents_sdk_integration.md

@@ -99,7 +99,7 @@ const agent = new GuardrailAgent({ config: configDict, ... });
 
 ## Next Steps
 
-- Use the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) to generate your configuration
+- Use the [Guardrails Wizard](https://guardrails.openai.com/) to generate your configuration
 - Explore available guardrails for your use case  
-- Learn about pipeline configuration in our [quickstart](./typescript-quickstart.md)
+- Learn about pipeline configuration in our [quickstart](./quickstart.md)
 - For more details on the OpenAI Agents SDK, refer to the [Agent SDK documentation](https://openai.github.io/openai-agents-js/).

docs/evals.md

@@ -14,8 +14,6 @@ npm run eval -- --config-path guardrails_config.json --dataset-path data.jsonl
 npm run eval -- --config-path guardrails_config.json --dataset-path data.jsonl --mode benchmark --models gpt-5 gpt-5-mini gpt-5-nano
 ```
 
-Test with included demo files in our [github repository](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails/src/guardrails/evals/eval_demo)
-
 ## Dependencies
 
 The evals tool is included with the TypeScript package. No additional dependencies are required.
@@ -41,7 +39,7 @@ The evals tool is included with the TypeScript package. No additional dependenci
 
 Export a configuration from the Guardrails Wizard UI and pass its path via `--config-path`.
 
-- Open the [Wizard UI](https://oaig-whisper-yonder-xnjpy2.vercel.app/guardrails)
+- Open the [Wizard UI](https://guardrails.openai.com/)
 - Configure the guardrails you want to evaluate
 - Use Export to download the config file (JSON)
 - Run the evaluator with `--config-path /path/to/exported_config.json`
@@ -162,4 +160,4 @@ npm run eval -- --config-path config.json --dataset-path data.jsonl --base-url h
 ## Next Steps
 
 - See the [API Reference](./ref/eval/guardrail_evals.md) for detailed documentation
-- Use [Wizard UI](https://oaig-whisper-yonder-xnjpy2.vercel.app/guardrails) for configuring guardrails without code
+- Use [Wizard UI](https://guardrails.openai.com/) for configuring guardrails without code

docs/examples.md

@@ -1,21 +1,21 @@
 # Examples
 
-Ready-to-run examples demonstrating Guardrails in various scenarios. See the [`examples/`](https://github.com/OpenAI-Early-Access/guardrails-js/tree/main/examples/) folder for complete implementations.
+Ready-to-run examples demonstrating Guardrails in various scenarios. See the [`examples/`](https://github.com/openai/openai-guardrails-js/tree/main/examples/) folder for complete implementations.
 
 ## Example Implementations
 
-- [hello_world.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/hello_world.ts) — Basic Guardrails usage
-- [agents_sdk.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/agents_sdk.ts) — OpenAI Agents SDK integration
-- [streaming.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/streaming.ts) — Streaming vs blocking usage
-- [suppress_tripwire.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/suppress_tripwire.ts) — Handle violations without raising
-- [multiturn_with_prompt injection detection.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/multiturn_with_prompt injection detection.ts) — Multi-turn with prompt injection detection
-- [azure_example.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/azure_example.ts) — Azure OpenAI client
-- [local_model.ts](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples/local_model.ts) — OpenAI-compatible local endpoint
+- [hello_world.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/hello_world.ts) — Basic Guardrails usage
+- [agents_sdk.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/agents_sdk.ts) — OpenAI Agents SDK integration
+- [streaming.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/streaming.ts) — Streaming vs blocking usage
+- [suppress_tripwire.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/suppress_tripwire.ts) — Handle violations without raising
+- [multiturn_with_prompt_injection_detection.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/multiturn_with_prompt_injection_detection.ts) — Multi-turn with prompt injection detection
+- [azure_example.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/azure_example.ts) — Azure OpenAI client
+- [local_model.ts](https://github.com/openai/openai-guardrails-js/tree/main/examples/basic/local_model.ts) — OpenAI-compatible local endpoint
 
 ## Getting Started
 
-1. Follow the Quickstart guide: [TypeScript](./typescript-quickstart.md)
-2. Explore examples: [TypeScript examples](https://github.com/OpenAI-Early-Access/guardrails-js/tree/main/examples/)
+1. Follow the Quickstart guide: [TypeScript](./quickstart.md)
+2. Explore examples: [TypeScript examples](https://github.com/openai/openai-guardrails-js/tree/main/examples/)
 3. Run scripts to see Guardrails in action
 
 Each example is self-contained with clear configuration and usage patterns.

docs/index.md

@@ -1,6 +1,6 @@
 # Guardrails
 
-**Guardrails** is a safety framework for LLM applications that automatically validates inputs and outputs using configurable checks. Use the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) to create configurations, then drop in our client classes for automatic validation.
+**Guardrails** is a safety framework for LLM applications that automatically validates inputs and outputs using configurable checks. Use the [Guardrails Wizard](https://guardrails.openai.com/) to create configurations, then drop in our client classes for automatic validation.
 
 ![Guardrails Wizard](assets/images/guardrails_wizard_screenshot.png)
 
@@ -53,9 +53,9 @@ main();
 
 ## Next Steps
 
-- [Quickstart: TypeScript](./typescript-quickstart.md)
+- [Quickstart](./quickstart.md)
 - [Examples](./examples.md) - See real implementations
-- [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) - Create configurations visually
+- [Guardrails Wizard](https://guardrails.openai.com/) - Create configurations visually
 
 ## Disclaimers
 

docs/typescript-quickstart.md renamed to docs/quickstart.md

@@ -16,7 +16,7 @@ export OPENAI_API_KEY=sk-...
 
 ## Create Pipeline Configuration
 
-The fastest way is using the [Guardrails Wizard](https://guardrails-vercel-git-main-openai.vercel.app/guardrails) - a no-code tool for creating configurations.
+The fastest way is using the [Guardrails Wizard](https://guardrails.openai.com/) - a no-code tool for creating configurations.
 
 Or define manually:
 
@@ -60,15 +60,7 @@ import { GuardrailsOpenAI } from '@guardrails/guardrails-ts';
 
 async function main() {
     // Use GuardrailsOpenAI instead of OpenAI
-    const client = await GuardrailsOpenAI.create({
-        version: 1,
-        output: {
-            version: 1,
-            guardrails: [
-                {"name": "Moderation", "config": {"categories": ["hate", "violence"]}}
-            ]
-        }
-    });
+    const client = await GuardrailsOpenAI.create('./guardrails_config.json');
 
     try {
         const response = await client.responses.create({
@@ -128,15 +120,11 @@ import { GuardrailAgent } from '@guardrails/guardrails-ts';
 import { Runner } from '@openai/agents';
 
 // Create agent with guardrails automatically configured
-const agent = await GuardrailAgent.create({
-    version: 1,
-    output: {
-        version: 1,
-        guardrails: [
-            {"name": "Moderation", "config": {"categories": ["hate", "violence"]}}
-        ]
-    }
-}, "Customer support agent", "You are a customer support agent. You help customers with their questions.");
+const agent = await GuardrailAgent.create(
+    './guardrails_config.json',
+    "Customer support agent",
+    "You are a customer support agent. You help customers with their questions."
+);
 
 // Use exactly like a regular Agent
 const result = await Runner.run(agent, "Hello, can you help me?");
@@ -151,19 +139,14 @@ Use the Azure-specific client:
 ```typescript
 import { GuardrailsAzureOpenAI } from '@guardrails/guardrails-ts';
 
-const client = await GuardrailsAzureOpenAI.create({
-    version: 1,
-    output: {
-        version: 1,
-        guardrails: [
-            {"name": "Moderation", "config": {"categories": ["hate", "violence"]}}
-        ]
+const client = await GuardrailsAzureOpenAI.create(
+    './guardrails_config.json',
+    {
+        azure_endpoint: "https://your-resource.openai.azure.com/",
+        api_key: "your-azure-key",
+        api_version: "2025-01-01-preview"
     }
-}, {
-    azure_endpoint: "https://your-resource.openai.azure.com/",
-    api_key: "your-azure-key",
-    api_version: "2025-01-01-preview"
-});
+);
 ```
 
 ## Third-Party Models
@@ -174,13 +157,16 @@ Works with any OpenAI-compatible API:
 import { GuardrailsOpenAI } from '@guardrails/guardrails-ts';
 
 // Local Ollama model
-const client = await GuardrailsOpenAI.create(config, {
-    baseURL: "http://127.0.0.1:11434/v1/",
-    apiKey: "ollama"
-});
+const client = await GuardrailsOpenAI.create(
+    './guardrails_config.json',
+    {
+        baseURL: "http://127.0.0.1:11434/v1/",
+        apiKey: "ollama"
+    }
+);
 ```
 
 ## Next Steps
 
-- Explore TypeScript [examples](https://github.com/OpenAI-Early-Access/guardrails/tree/main/guardrails-ts/examples) for advanced patterns
+- Explore TypeScript [examples](https://github.com/openai/openai-guardrails-js/tree/main/examples) for advanced patterns
 - Learn about [streaming considerations](./streaming_output.md)

docs/ref/checks/hallucination_detection.md

@@ -80,7 +80,7 @@ console.log(response.llm_response.output_text);
 
 ### Complete Example
 
-See [`examples/`](https://github.com/openai/guardrails-js/tree/main/examples) for the full implementation.
+See [`examples/`](https://github.com/openai/openai-guardrails-js/tree/main/examples) for the full implementation.
 
 ### Notes
 

docs/ref/exceptions-typescript.md

@@ -23,6 +23,6 @@ export class GuardrailExecutionError extends GuardrailError {
 - `GuardrailNotFoundError`: referenced guardrail name not registered.
 - `GuardrailExecutionError`: runtime failure within a guardrail (optional `cause`).
 
-For the full source, see [guardrails-ts/src/exceptions.ts](https://github.com/OpenAI-Early-Access/guardrails/blob/main/guardrails-ts/src/exceptions.ts) in the repository.
+For the full source, see [src/exceptions.ts](https://github.com/openai/openai-guardrails-js/blob/main/src/exceptions.ts) in the repository.
 
 

docs/ref/types-typescript.md

@@ -58,6 +58,6 @@ export type TIn = unknown;
 export type TCfg = object;
 ```
 
-For the full source, see [guardrails-ts/src/types.ts](https://github.com/OpenAI-Early-Access/guardrails/blob/main/guardrails-ts/src/types.ts) in the repository.
+For the full source, see [src/types.ts](https://github.com/openai/openai-guardrails-js/blob/main/src/types.ts) in the repository.
 
 

docs/streaming_output.md

@@ -42,10 +42,3 @@ const response = await client.responses.create({
   stream: true  // Fast but some risk
 });
 ```
-
-## Implementation Examples
-
-See complete examples:
-
-- [Non-streaming (safe)](https://github.com/OpenAI-Early-Access/guardrails-js/tree/main/examples)
-- [Streaming (fast)](https://github.com/OpenAI-Early-Access/guardrails-js/tree/main/examples)