diff --git a/.github/workflows/manual-publish-docs.yml b/.github/workflows/manual-publish-docs.yml
index 397bc1a58e..907b270001 100644
--- a/.github/workflows/manual-publish-docs.yml
+++ b/.github/workflows/manual-publish-docs.yml
@@ -20,6 +20,7 @@ on:
           - packages/store/node-server-sdk-dynamodb
           - packages/telemetry/node-server-sdk-otel
           - packages/sdk/browser
+          - packages/sdk/server-ai
 name: Publish Documentation
 jobs:
   build-publish:
diff --git a/.github/workflows/manual-publish.yml b/.github/workflows/manual-publish.yml
index c8ba253ade..c1ca69e3b3 100644
--- a/.github/workflows/manual-publish.yml
+++ b/.github/workflows/manual-publish.yml
@@ -33,6 +33,7 @@ on:
           - packages/telemetry/node-server-sdk-otel
           - packages/tooling/jest
           - packages/sdk/browser
+          - packages/sdk/server-ai
       prerelease:
         description: 'Is this a prerelease. If so, then the latest tag will not be updated in npm.'
         type: boolean
diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index 57a260d962..33b7a55f1f 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -25,6 +25,7 @@ jobs:
       package-tooling-jest-release: ${{ steps.release.outputs['packages/tooling/jest--release_created'] }}
       package-react-universal-release: ${{ steps.release.outputs['packages/sdk/react-universal--release_created'] }}
       package-browser-released: ${{ steps.release.outputs['packages/sdk/browser--release_created'] }}
+      package-server-ai-released: ${{ steps.release.outputs['packages/sdk/server-ai--release_created'] }}
     steps:
       - uses: googleapis/release-please-action@v4
         id: release
@@ -377,3 +378,23 @@ jobs:
         with:
           workspace_path: packages/sdk/react-universal
           aws_assume_role: ${{ vars.AWS_ROLE_ARN }}
+
+  release-server-ai:
+    runs-on: ubuntu-latest
+    needs: ['release-please', 'release-sdk-server']
+    permissions:
+      id-token: write
+      contents: write
+    if: ${{ always() && !failure() && !cancelled() && needs.release-please.outputs.package-server-ai-released == 'true'}}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20.x
+          registry-url: 'https://registry.npmjs.org'
+      - id: release-react-native
+        name: Full release of packages/sdk/server-ai
+        uses: ./actions/full-release
+        with:
+          workspace_path: packages/sdk/server-ai
+          aws_assume_role: ${{ vars.AWS_ROLE_ARN }}
diff --git a/.github/workflows/server-ai.yml b/.github/workflows/server-ai.yml
new file mode 100644
index 0000000000..e403cb52ec
--- /dev/null
+++ b/.github/workflows/server-ai.yml
@@ -0,0 +1,37 @@
+name: sdk/server-ai
+
+on:
+  push:
+    branches: [main, 'feat/**']
+    paths-ignore:
+      - '**.md' #Do not need to run CI for markdown changes.
+  pull_request:
+    branches: [main, 'feat/**']
+    paths-ignore:
+      - '**.md'
+
+jobs:
+  build-test-node-server-otel:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20.x
+          registry-url: 'https://registry.npmjs.org'
+      - id: shared
+        name: Shared CI Steps
+        uses: ./actions/ci
+        with:
+          workspace_name: '@launchdarkly/server-sdk-ai'
+          workspace_path: packages/sdk/server-ai
+      - name: Build bedrock example
+        run: |
+          yarn workspaces focus @launchdarkly/hello-ai-bedrock
+          yarn workspace @launchdarkly/hello-ai-bedrock lint
+          yarn workspaces foreach -pR --topological-dev --from '@launchdarkly/hello-ai-bedrock' run build
+      - name: Build OpenAI example
+        run: |
+          yarn workspaces focus @launchdarkly/hello-openai
+          yarn workspace @launchdarkly/hello-openai lint
+          yarn workspaces foreach -pR --topological-dev --from '@launchdarkly/hello-openai' run build
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 262b815739..719eb98c30 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -13,5 +13,6 @@
   "packages/shared/sdk-client": "1.12.0",
   "packages/sdk/react-native": "10.9.2",
   "packages/telemetry/node-server-sdk-otel": "1.1.1",
-  "packages/sdk/browser": "0.3.0"
+  "packages/sdk/browser": "0.3.0",
+  "packages/sdk/server-ai": "0.0.0"
 }
diff --git a/package.json b/package.json
index eb764fee94..38052de4db 100644
--- a/package.json
+++ b/package.json
@@ -25,7 +25,10 @@
     "packages/tooling/jest/example/react-native-example",
     "packages/sdk/browser",
     "packages/sdk/browser/contract-tests/entity",
-    "packages/sdk/browser/contract-tests/adapter"
+    "packages/sdk/browser/contract-tests/adapter",
+    "packages/sdk/server-ai",
+    "packages/sdk/server-ai/examples/bedrock",
+    "packages/sdk/server-ai/examples/openai"
   ],
   "private": true,
   "scripts": {
diff --git a/packages/sdk/server-ai/README.md b/packages/sdk/server-ai/README.md
new file mode 100644
index 0000000000..e4ae013f12
--- /dev/null
+++ b/packages/sdk/server-ai/README.md
@@ -0,0 +1,68 @@
+# LaunchDarkly AI SDK for Server-Side JavaScript
+
+# ⛔️⛔️⛔️⛔️
+
+> [!CAUTION]
+> This library is a alpha version and should not be considered ready for production use while this message is visible.
+
+# ☝️☝️☝️☝️☝️☝️
+
+## LaunchDarkly overview
+
+[LaunchDarkly](https://www.launchdarkly.com) is a feature management platform that serves over 100 billion feature flags daily to help teams build better software, faster. [Get started](https://docs.launchdarkly.com/home/getting-started) using LaunchDarkly today!
+
+[![Twitter Follow](https://img.shields.io/twitter/follow/launchdarkly.svg?style=social&label=Follow&maxAge=2592000)](https://twitter.com/intent/follow?screen_name=launchdarkly)
+
+## Quick Setup
+
+This assumes that you have already installed the LaunchDarkly Node.js SDK, or a compatible edge
+SDK.
+
+1. Install this package with `npm` or `yarn`:
+
+```shell
+npm install @launchdarkly/server-sdk-ai --save
+```
+
+2. Create an AI SDK instance:
+
+```typescript
+// The ldClient instance should be created based on the instructions in the relevant SDK.
+const aiClient = initAi(ldClient);
+```
+
+3. Evaluate a model configuration:
+```typescript
+  const config = await aiClient.modelConfig(
+    aiConfigKey!,
+    context,
+    { enabled: false },
+    { myVariable: 'My User Defined Variable' },
+  );
+```
+
+For an example of how to use the config please refer to the examples folder.
+
+## Contributing
+
+We encourage pull requests and other contributions from the community. Check out our [contributing guidelines](CONTRIBUTING.md) for instructions on how to contribute to this SDK.
+
+## About LaunchDarkly
+
+- LaunchDarkly is a continuous delivery platform that provides feature flags as a service and allows developers to iterate quickly and safely. We allow you to easily flag your features and manage them from the LaunchDarkly dashboard. With LaunchDarkly, you can:
+  - Roll out a new feature to a subset of your users (like a group of users who opt-in to a beta tester group), gathering feedback and bug reports from real-world use cases.
+  - Gradually roll out a feature to an increasing percentage of users, and track the effect that the feature has on key metrics (for instance, how likely is a user to complete a purchase if they have feature A versus feature B?).
+  - Turn off a feature that you realize is causing performance problems in production, without needing to re-deploy, or even restart the application with a changed configuration file.
+  - Grant access to certain features based on user attributes, like payment plan (eg: users on the ‘gold’ plan get access to more features than users in the ‘silver’ plan).
+  - Disable parts of your application to facilitate maintenance, without taking everything offline.
+- LaunchDarkly provides feature flag SDKs for a wide variety of languages and technologies. Check out [our documentation](https://docs.launchdarkly.com/sdk) for a complete list.
+- Explore LaunchDarkly
+  - [launchdarkly.com](https://www.launchdarkly.com/ 'LaunchDarkly Main Website') for more information
+  - [docs.launchdarkly.com](https://docs.launchdarkly.com/ 'LaunchDarkly Documentation') for our documentation and SDK reference guides
+  - [apidocs.launchdarkly.com](https://apidocs.launchdarkly.com/ 'LaunchDarkly API Documentation') for our API documentation
+  - [blog.launchdarkly.com](https://blog.launchdarkly.com/ 'LaunchDarkly Blog Documentation') for the latest product updates
+
+[node-otel-ci-badge]: https://github.com/launchdarkly/js-core/actions/workflows/node-otel.yml/badge.svg
+[node-otel-ci]: https://github.com/launchdarkly/js-core/actions/workflows/node-otel.yml
+[node-otel-npm-badge]: https://img.shields.io/npm/v/@launchdarkly/node-server-sdk-otel.svg?style=flat-square
+[node-otel-npm-link]: https://www.npmjs.com/package/@launchdarkly/node-server-sdk-otel
diff --git a/packages/sdk/server-ai/examples/bedrock/README.md b/packages/sdk/server-ai/examples/bedrock/README.md
new file mode 100644
index 0000000000..a997129f82
--- /dev/null
+++ b/packages/sdk/server-ai/examples/bedrock/README.md
@@ -0,0 +1,46 @@
+# LaunchDarkly AI SDK for AWS Bedrock Example
+
+This package demonstrates the integration of LaunchDarkly's AI SDK with AWS Bedrock, allowing you to leverage LaunchDarkly's AI Config capabilities in AI-powered applications using AWS Bedrock.
+
+## Installation and Build
+
+When running as part of the js-core mono-repo the project will use local dependencies.
+As such those dependencies need built.
+
+In the root of the repository run:
+
+```bash
+yarn
+```
+
+And then
+
+```bash
+yarn build
+```
+
+## Configuration
+
+Before running the example, make sure to set the following environment variables:
+
+- `LAUNCHDARKLY_SDK_KEY`: Your LaunchDarkly SDK key
+- `LAUNCHDARKLY_AI_CONFIG_KEY`: Your LaunchDarkly AI configuration key (defaults to 'sample-ai-config' if not set)
+
+Additionally, ensure you have proper AWS credentials configured to access Bedrock services.
+
+## Usage
+
+The main script (`index.js`) demonstrates how to:
+
+1. Initialize the LaunchDarkly SDK
+2. Set up a user context
+3. Initialize the LaunchDarkly AI client
+4. Retrieve an AI model configuration
+5. Send a prompt to AWS Bedrock
+6. Track token usage
+
+To run the example (in the bedrock directory):
+
+```bash
+yarn start
+```
diff --git a/packages/sdk/server-ai/examples/bedrock/package.json b/packages/sdk/server-ai/examples/bedrock/package.json
new file mode 100644
index 0000000000..1461cee305
--- /dev/null
+++ b/packages/sdk/server-ai/examples/bedrock/package.json
@@ -0,0 +1,54 @@
+{
+  "name": "@launchdarkly/hello-ai-bedrock",
+  "version": "0.1.0",
+  "description": "LaunchDarkly AI SDK for Node.js",
+  "private": true,
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "type": "commonjs",
+  "scripts": {
+    "build": "tsc",
+    "start": "yarn build && node ./dist/index.js",
+    "lint": "npx eslint . --ext .ts",
+    "prettier": "prettier --write '**/*.@(js|ts|tsx|json|css)' --ignore-path ../../../.prettierignore",
+    "lint:fix": "yarn run lint --fix",
+    "check": "yarn prettier && yarn lint && yarn build && yarn test"
+  },
+  "keywords": [
+    "launchdarkly",
+    "ai",
+    "llm"
+  ],
+  "author": "LaunchDarkly",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "@aws-sdk/client-bedrock-runtime": "^3.679.0",
+    "@launchdarkly/node-server-sdk": "^9.7.1",
+    "@launchdarkly/server-sdk-ai": "0.1.0"
+  },
+  "devDependencies": {
+    "@trivago/prettier-plugin-sort-imports": "^4.1.1",
+    "@tsconfig/node20": "20.1.4",
+    "@typescript-eslint/eslint-plugin": "^6.20.0",
+    "@typescript-eslint/parser": "^6.20.0",
+    "eslint": "^8.45.0",
+    "eslint-config-airbnb-base": "^15.0.0",
+    "eslint-config-airbnb-typescript": "^17.1.0",
+    "eslint-config-prettier": "^8.8.0",
+    "eslint-plugin-import": "^2.27.5",
+    "eslint-plugin-jest": "^27.6.3",
+    "eslint-plugin-prettier": "^5.0.0",
+    "jest": "^29.7.0",
+    "prettier": "^3.0.0",
+    "rimraf": "^5.0.5",
+    "typedoc": "0.25.0",
+    "typescript": "^5.5.3"
+  },
+  "directories": {
+    "example": "example"
+  },
+  "repository": {
+    "type": "git",
+    "url": "github.com/launchdarkly/js-core"
+  }
+}
diff --git a/packages/sdk/server-ai/examples/bedrock/src/index.ts b/packages/sdk/server-ai/examples/bedrock/src/index.ts
new file mode 100644
index 0000000000..95bd83da60
--- /dev/null
+++ b/packages/sdk/server-ai/examples/bedrock/src/index.ts
@@ -0,0 +1,78 @@
+/* eslint-disable no-console */
+import { BedrockRuntimeClient, ConverseCommand, Message } from '@aws-sdk/client-bedrock-runtime';
+
+import { init } from '@launchdarkly/node-server-sdk';
+import { initAi } from '@launchdarkly/server-sdk-ai';
+
+const sdkKey = process.env.LAUNCHDARKLY_SDK_KEY;
+const aiConfigKey = process.env.LAUNCHDARKLY_AI_CONFIG_KEY || 'sample-ai-config';
+const awsClient = new BedrockRuntimeClient({ region: 'us-east-1' });
+
+if (!sdkKey) {
+  console.error('*** Please set the LAUNCHDARKLY_SDK_KEY env first');
+  process.exit(1);
+}
+
+if (!aiConfigKey) {
+  console.error('*** Please set the LAUNCHDARKLY_AI_CONFIG_KEY env first');
+  process.exit(1);
+}
+
+const ldClient = init(sdkKey);
+
+// Set up the context properties
+const context = {
+  kind: 'user',
+  key: 'example-user-key',
+  name: 'Sandy',
+};
+
+function mapPromptToConversation(
+  prompt: { role: 'user' | 'assistant' | 'system'; content: string }[],
+): Message[] {
+  return prompt.map((item) => ({
+    // Bedrock doesn't support systems in the converse command.
+    role: item.role !== 'system' ? item.role : 'user',
+    content: [{ text: item.content }],
+  }));
+}
+
+async function main() {
+  try {
+    await ldClient.waitForInitialization({ timeout: 10 });
+    console.log('*** SDK successfully initialized');
+  } catch (error) {
+    console.log(`*** SDK failed to initialize: ${error}`);
+    process.exit(1);
+  }
+
+  const aiClient = initAi(ldClient);
+
+  const aiConfig = await aiClient.modelConfig(
+    aiConfigKey!,
+    context,
+    {
+      model: {
+        modelId: 'my-default-model',
+      },
+      enabled: true,
+    },
+    {
+      myVariable: 'My User Defined Variable',
+    },
+  );
+  const { tracker } = aiConfig;
+
+  const completion = tracker.trackBedrockConverse(
+    await awsClient.send(
+      new ConverseCommand({
+        modelId: aiConfig.config.model?.modelId ?? 'no-model',
+        messages: mapPromptToConversation(aiConfig.config.prompt ?? []),
+      }),
+    ),
+  );
+  console.log('AI Response:', completion.output?.message?.content?.[0]?.text ?? 'no-response');
+  console.log('Success.');
+}
+
+main();
diff --git a/packages/sdk/server-ai/examples/bedrock/tsconfig.eslint.json b/packages/sdk/server-ai/examples/bedrock/tsconfig.eslint.json
new file mode 100644
index 0000000000..8241f86c36
--- /dev/null
+++ b/packages/sdk/server-ai/examples/bedrock/tsconfig.eslint.json
@@ -0,0 +1,5 @@
+{
+  "extends": "./tsconfig.json",
+  "include": ["/**/*.ts", "/**/*.tsx"],
+  "exclude": ["node_modules"]
+}
diff --git a/packages/sdk/server-ai/examples/bedrock/tsconfig.json b/packages/sdk/server-ai/examples/bedrock/tsconfig.json
new file mode 100644
index 0000000000..5a491900d3
--- /dev/null
+++ b/packages/sdk/server-ai/examples/bedrock/tsconfig.json
@@ -0,0 +1,22 @@
+{
+  "extends": "@tsconfig/node20/tsconfig.json",
+  "compilerOptions": {
+    "noEmit": false,
+    "outDir": "dist",
+    "baseUrl": ".",
+    "allowUnusedLabels": false,
+    "allowUnreachableCode": false,
+    "noFallthroughCasesInSwitch": true,
+    "noUncheckedIndexedAccess": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "forceConsistentCasingInFileNames": true,
+    "declaration": true,
+    "sourceMap": true,
+    "resolveJsonModule": true,
+    "module": "CommonJS",
+    "moduleResolution": "Node"
+  },
+  "include": ["src"],
+  "exclude": ["dist", "node_modules"]
+}
diff --git a/packages/sdk/server-ai/examples/openai/README.md b/packages/sdk/server-ai/examples/openai/README.md
new file mode 100644
index 0000000000..0126c332ad
--- /dev/null
+++ b/packages/sdk/server-ai/examples/openai/README.md
@@ -0,0 +1,50 @@
+# LaunchDarkly AI SDK for OpenAI Example
+
+This package demonstrates the integration of LaunchDarkly's AI SDK with OpenAI, allowing you to leverage LaunchDarkly's AI Config capabilities in AI-powered applications using OpenAI's services.
+
+## Installation and Build
+
+
+When running as part of the js-core mono-repo the project will use local dependencies.
+As such those dependencies need built.
+
+In the root of the repository run:
+
+```bash
+yarn
+```
+
+And then
+
+```bash
+yarn build
+```
+
+## Configuration
+
+Before running the example, make sure to set the following environment variables:
+
+- `LAUNCHDARKLY_SDK_KEY`: Your LaunchDarkly SDK key
+- `LAUNCHDARKLY_AI_CONFIG_KEY`: Your LaunchDarkly AI configuration key (defaults to 'sample-ai-config' if not set)
+- `OPENAI_API_KEY`: Your OpenAI API key
+
+## Usage
+
+The main script (`index.js`) demonstrates how to:
+
+1. Initialize the LaunchDarkly SDK
+2. Set up a user context
+3. Initialize the LaunchDarkly AI client
+4. Retrieve an AI model configuration
+5. Send a prompt to OpenAI
+6. Track token usage
+
+To run the example (in the openai directory):
+
+```bash
+yarn start
+```
+
+## Note
+
+This example uses OpenAI's chat completions API. Make sure your LaunchDarkly AI configuration is set up correctly to work with OpenAI's models and API structure.
diff --git a/packages/sdk/server-ai/examples/openai/package.json b/packages/sdk/server-ai/examples/openai/package.json
new file mode 100644
index 0000000000..6d4b74831a
--- /dev/null
+++ b/packages/sdk/server-ai/examples/openai/package.json
@@ -0,0 +1,53 @@
+{
+  "name": "@launchdarkly/hello-openai",
+  "version": "0.1.0",
+  "description": "LaunchDarkly AI SDK for Node.js",
+  "private": true,
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "scripts": {
+    "build": "tsc",
+    "start": "yarn build && node ./dist/index.js",
+    "lint": "npx eslint . --ext .ts",
+    "prettier": "prettier --write '**/*.@(js|ts|tsx|json|css)' --ignore-path ../../../.prettierignore",
+    "lint:fix": "yarn run lint --fix",
+    "check": "yarn prettier && yarn lint && yarn build && yarn test"
+  },
+  "keywords": [
+    "launchdarkly",
+    "ai",
+    "llm"
+  ],
+  "author": "LaunchDarkly",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "@launchdarkly/node-server-sdk": "^9.7.1",
+    "@launchdarkly/server-sdk-ai": "0.1.0",
+    "openai": "^4.58.1"
+  },
+  "devDependencies": {
+    "@trivago/prettier-plugin-sort-imports": "^4.1.1",
+    "@tsconfig/node20": "20.1.4",
+    "@typescript-eslint/eslint-plugin": "^6.20.0",
+    "@typescript-eslint/parser": "^6.20.0",
+    "eslint": "^8.45.0",
+    "eslint-config-airbnb-base": "^15.0.0",
+    "eslint-config-airbnb-typescript": "^17.1.0",
+    "eslint-config-prettier": "^8.8.0",
+    "eslint-plugin-import": "^2.27.5",
+    "eslint-plugin-jest": "^27.6.3",
+    "eslint-plugin-prettier": "^5.0.0",
+    "jest": "^29.7.0",
+    "prettier": "^3.0.0",
+    "rimraf": "^5.0.5",
+    "typedoc": "0.25.0",
+    "typescript": "^5.5.3"
+  },
+  "directories": {
+    "example": "example"
+  },
+  "repository": {
+    "type": "git",
+    "url": "github.com/launchdarkly/js-core"
+  }
+}
diff --git a/packages/sdk/server-ai/examples/openai/src/index.ts b/packages/sdk/server-ai/examples/openai/src/index.ts
new file mode 100644
index 0000000000..041d1f076e
--- /dev/null
+++ b/packages/sdk/server-ai/examples/openai/src/index.ts
@@ -0,0 +1,72 @@
+/* eslint-disable no-console */
+import { OpenAI } from 'openai';
+
+import { init, LDContext } from '@launchdarkly/node-server-sdk';
+import { initAi } from '@launchdarkly/server-sdk-ai';
+
+// Environment variables
+const sdkKey = process.env.LAUNCHDARKLY_SDK_KEY;
+const aiConfigKey = process.env.LAUNCHDARKLY_AI_CONFIG_KEY || 'sample-ai-config';
+
+// Initialize OpenAI client
+const client = new OpenAI({
+  apiKey: process.env.OPENAI_API_KEY, // This is the default and can be omitted
+});
+
+// Validate required environment variables
+if (!sdkKey) {
+  console.error('*** Please set the LAUNCHDARKLY_SDK_KEY env first');
+  process.exit(1);
+}
+
+if (!aiConfigKey) {
+  console.error('*** Please set the LAUNCHDARKLY_AI_CONFIG_KEY env first');
+  process.exit(1);
+}
+
+// Initialize LaunchDarkly client
+const ldClient = init(sdkKey);
+
+// Set up the context properties. This context should appear on your LaunchDarkly contexts dashboard
+// soon after you run the demo.
+const context: LDContext = {
+  kind: 'user',
+  key: 'example-user-key',
+  name: 'Sandy',
+};
+
+async function main(): Promise<void> {
+  try {
+    await ldClient.waitForInitialization({ timeout: 10 });
+    console.log('*** SDK successfully initialized');
+  } catch (error) {
+    console.log(`*** SDK failed to initialize: ${error}`);
+    process.exit(1);
+  }
+
+  const aiClient = initAi(ldClient);
+
+  const aiConfig = await aiClient.modelConfig(
+    aiConfigKey,
+    context,
+    {
+      model: {
+        modelId: 'gpt-4',
+      },
+    },
+    { myVariable: 'My User Defined Variable' },
+  );
+
+  const { tracker } = aiConfig;
+  const completion = await tracker.trackOpenAI(async () =>
+    client.chat.completions.create({
+      messages: aiConfig.config.prompt || [],
+      model: aiConfig.config.model?.modelId || 'gpt-4',
+    }),
+  );
+
+  console.log('AI Response:', completion.choices[0]?.message.content);
+  console.log('Success.');
+}
+
+main();
diff --git a/packages/sdk/server-ai/examples/openai/tsconfig.eslint.json b/packages/sdk/server-ai/examples/openai/tsconfig.eslint.json
new file mode 100644
index 0000000000..8241f86c36
--- /dev/null
+++ b/packages/sdk/server-ai/examples/openai/tsconfig.eslint.json
@@ -0,0 +1,5 @@
+{
+  "extends": "./tsconfig.json",
+  "include": ["/**/*.ts", "/**/*.tsx"],
+  "exclude": ["node_modules"]
+}
diff --git a/packages/sdk/server-ai/examples/openai/tsconfig.json b/packages/sdk/server-ai/examples/openai/tsconfig.json
new file mode 100644
index 0000000000..5a491900d3
--- /dev/null
+++ b/packages/sdk/server-ai/examples/openai/tsconfig.json
@@ -0,0 +1,22 @@
+{
+  "extends": "@tsconfig/node20/tsconfig.json",
+  "compilerOptions": {
+    "noEmit": false,
+    "outDir": "dist",
+    "baseUrl": ".",
+    "allowUnusedLabels": false,
+    "allowUnreachableCode": false,
+    "noFallthroughCasesInSwitch": true,
+    "noUncheckedIndexedAccess": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "forceConsistentCasingInFileNames": true,
+    "declaration": true,
+    "sourceMap": true,
+    "resolveJsonModule": true,
+    "module": "CommonJS",
+    "moduleResolution": "Node"
+  },
+  "include": ["src"],
+  "exclude": ["dist", "node_modules"]
+}
diff --git a/packages/sdk/server-ai/package.json b/packages/sdk/server-ai/package.json
new file mode 100644
index 0000000000..2af0e192d7
--- /dev/null
+++ b/packages/sdk/server-ai/package.json
@@ -0,0 +1,48 @@
+{
+  "name": "@launchdarkly/server-sdk-ai",
+  "version": "0.1.0",
+  "description": "LaunchDarkly AI SDK for Server-Side JavaScript",
+  "main": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "type": "commonjs",
+  "scripts": {
+    "build": "npx tsc",
+    "lint": "npx eslint . --ext .ts",
+    "prettier": "prettier --write '**/*.@(js|ts|tsx|json|css)' --ignore-path ../../../.prettierignore",
+    "lint:fix": "yarn run lint --fix",
+    "check": "yarn prettier && yarn lint && yarn build && yarn test",
+    "test": "echo No tests added yet."
+  },
+  "keywords": [
+    "launchdarkly",
+    "ai",
+    "llm"
+  ],
+  "author": "LaunchDarkly",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "mustache": "^4.2.0"
+  },
+  "devDependencies": {
+    "@launchdarkly/js-server-sdk-common": "2.9.0",
+    "@trivago/prettier-plugin-sort-imports": "^4.1.1",
+    "@types/jest": "^29.5.3",
+    "@types/mustache": "^4.2.5",
+    "@typescript-eslint/eslint-plugin": "^6.20.0",
+    "@typescript-eslint/parser": "^6.20.0",
+    "eslint": "^8.45.0",
+    "eslint-config-airbnb-base": "^15.0.0",
+    "eslint-config-airbnb-typescript": "^17.1.0",
+    "eslint-config-prettier": "^8.8.0",
+    "eslint-plugin-import": "^2.27.5",
+    "eslint-plugin-jest": "^27.6.3",
+    "eslint-plugin-prettier": "^5.0.0",
+    "jest": "^29.6.1",
+    "prettier": "^3.0.0",
+    "ts-jest": "^29.1.1",
+    "typescript": "5.1.6"
+  },
+  "peerDependencies": {
+    "@launchdarkly/js-server-sdk-common": "2.x"
+  }
+}
diff --git a/packages/sdk/server-ai/src/LDAIClientImpl.ts b/packages/sdk/server-ai/src/LDAIClientImpl.ts
new file mode 100644
index 0000000000..dd0dead9d0
--- /dev/null
+++ b/packages/sdk/server-ai/src/LDAIClientImpl.ts
@@ -0,0 +1,68 @@
+import * as Mustache from 'mustache';
+
+import { LDContext } from '@launchdarkly/js-server-sdk-common';
+
+import { LDAIConfig, LDGenerationConfig, LDMessage, LDModelConfig } from './api/config';
+import { LDAIClient } from './api/LDAIClient';
+import { LDAIConfigTrackerImpl } from './LDAIConfigTrackerImpl';
+import { LDClientMin } from './LDClientMin';
+
+/**
+ * Metadata assorted with a model configuration variation.
+ */
+interface LDMeta {
+  versionKey: string;
+  enabled: boolean;
+}
+
+/**
+ * Interface for the model configuration variation returned by LaunchDarkly. This is the internal
+ * typing and not meant for exposure to the application developer.
+ */
+interface VariationContent {
+  model?: LDModelConfig;
+  prompt?: LDMessage[];
+  _ldMeta?: LDMeta;
+}
+
+export class LDAIClientImpl implements LDAIClient {
+  constructor(private _ldClient: LDClientMin) {}
+
+  interpolateTemplate(template: string, variables: Record<string, unknown>): string {
+    return Mustache.render(template, variables, undefined, { escape: (item: any) => item });
+  }
+
+  async modelConfig<TDefault extends LDGenerationConfig>(
+    key: string,
+    context: LDContext,
+    defaultValue: TDefault,
+    variables?: Record<string, unknown>,
+  ): Promise<LDAIConfig> {
+    const value: VariationContent = await this._ldClient.variation(key, context, defaultValue);
+    // We are going to modify the contents before returning them, so we make a copy.
+    // This isn't a deep copy and the application developer should not modify the returned content.
+    const config: LDGenerationConfig = { ...value };
+    const allVariables = { ...variables, ldctx: context };
+
+    if (value.prompt) {
+      config.prompt = value.prompt.map((entry: any) => ({
+        ...entry,
+        content: this.interpolateTemplate(entry.content, allVariables),
+      }));
+    }
+
+    return {
+      config,
+      // eslint-disable-next-line no-underscore-dangle
+      tracker: new LDAIConfigTrackerImpl(
+        this._ldClient,
+        key,
+        // eslint-disable-next-line no-underscore-dangle
+        value._ldMeta?.versionKey ?? '',
+        context,
+      ),
+      // eslint-disable-next-line no-underscore-dangle
+      enabled: !!value._ldMeta?.enabled,
+    };
+  }
+}
diff --git a/packages/sdk/server-ai/src/LDAIConfigTrackerImpl.ts b/packages/sdk/server-ai/src/LDAIConfigTrackerImpl.ts
new file mode 100644
index 0000000000..763d5bf112
--- /dev/null
+++ b/packages/sdk/server-ai/src/LDAIConfigTrackerImpl.ts
@@ -0,0 +1,102 @@
+import { LDContext } from '@launchdarkly/js-server-sdk-common';
+
+import { LDAIConfigTracker } from './api/config';
+import { createBedrockTokenUsage, LDFeedbackKind, LDTokenUsage } from './api/metrics';
+import { createOpenAiUsage } from './api/metrics/OpenAiUsage';
+import { LDClientMin } from './LDClientMin';
+
+export class LDAIConfigTrackerImpl implements LDAIConfigTracker {
+  constructor(
+    private _ldClient: LDClientMin,
+    private _configKey: string,
+    private _versionKey: string,
+    private _context: LDContext,
+  ) {}
+
+  private _getTrackData(): { versionKey: string; configKey: string } {
+    return {
+      versionKey: this._versionKey,
+      configKey: this._configKey,
+    };
+  }
+
+  trackDuration(duration: number): void {
+    this._ldClient.track('$ld:ai:duration:total', this._context, this._getTrackData(), duration);
+  }
+
+  async trackDurationOf<TRes>(func: () => Promise<TRes>): Promise<TRes> {
+    const startTime = Date.now();
+    const result = await func();
+    const endTime = Date.now();
+    const duration = endTime - startTime; // duration in milliseconds
+    this.trackDuration(duration);
+    return result;
+  }
+
+  trackFeedback(feedback: { kind: LDFeedbackKind }): void {
+    if (feedback.kind === LDFeedbackKind.Positive) {
+      this._ldClient.track('$ld:ai:feedback:user:positive', this._context, this._getTrackData(), 1);
+    } else if (feedback.kind === LDFeedbackKind.Negative) {
+      this._ldClient.track('$ld:ai:feedback:user:negative', this._context, this._getTrackData(), 1);
+    }
+  }
+
+  trackSuccess(): void {
+    this._ldClient.track('$ld:ai:generation', this._context, this._getTrackData(), 1);
+  }
+
+  async trackOpenAI<
+    TRes extends {
+      usage?: {
+        total_tokens?: number;
+        prompt_tokens?: number;
+        completion_tokens?: number;
+      };
+    },
+  >(func: () => Promise<TRes>): Promise<TRes> {
+    const result = await this.trackDurationOf(func);
+    this.trackSuccess();
+    if (result.usage) {
+      this.trackTokens(createOpenAiUsage(result.usage));
+    }
+    return result;
+  }
+
+  trackBedrockConverse<
+    TRes extends {
+      $metadata: { httpStatusCode?: number };
+      metrics?: { latencyMs?: number };
+      usage?: {
+        inputTokens?: number;
+        outputTokens?: number;
+        totalTokens?: number;
+      };
+    },
+  >(res: TRes): TRes {
+    if (res.$metadata?.httpStatusCode === 200) {
+      this.trackSuccess();
+    } else if (res.$metadata?.httpStatusCode && res.$metadata.httpStatusCode >= 400) {
+      // Potentially add error tracking in the future.
+    }
+    if (res.metrics && res.metrics.latencyMs) {
+      this.trackDuration(res.metrics.latencyMs);
+    }
+    if (res.usage) {
+      this.trackTokens(createBedrockTokenUsage(res.usage));
+    }
+    return res;
+  }
+
+  trackTokens(tokens: LDTokenUsage): void {
+    const trackData = this._getTrackData();
+    if (tokens.total > 0) {
+      this._ldClient.track('$ld:ai:tokens:total', this._context, trackData, tokens.total);
+    }
+    if (tokens.input > 0) {
+      this._ldClient.track('$ld:ai:tokens:input', this._context, trackData, tokens.input);
+    }
+    if (tokens.output > 0) {
+      this._ldClient.track('$ld:ai:tokens:output', this._context, trackData, tokens.output);
+    }
+  }
+}
diff --git a/packages/sdk/server-ai/src/LDClientMin.ts b/packages/sdk/server-ai/src/LDClientMin.ts
new file mode 100644
index 0000000000..2158c569cc
--- /dev/null
+++ b/packages/sdk/server-ai/src/LDClientMin.ts
@@ -0,0 +1,16 @@
+import { LDContext, LDFlagValue } from '@launchdarkly/js-server-sdk-common';
+
+/**
+ * Interface which represents the required interface components for a sever SDK
+ * to work with the AI SDK.
+ */
+export interface LDClientMin {
+  variation(
+    key: string,
+    context: LDContext,
+    defaultValue: LDFlagValue,
+    callback?: (err: any, res: LDFlagValue) => void,
+  ): Promise<LDFlagValue>;
+
+  track(key: string, context: LDContext, data?: any, metricValue?: number): void;
+}
diff --git a/packages/sdk/server-ai/src/api/LDAIClient.ts b/packages/sdk/server-ai/src/api/LDAIClient.ts
new file mode 100644
index 0000000000..ceaf936af3
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/LDAIClient.ts
@@ -0,0 +1,70 @@
+import { LDContext } from '@launchdarkly/js-server-sdk-common';
+
+import { LDAIConfig, LDGenerationConfig } from './config/LDAIConfig';
+
+/**
+ * Interface for performing AI operations using LaunchDarkly.
+ */
+
+export interface LDAIClient {
+  /**
+   * Parses and interpolates a template string with the provided variables.
+   *
+   * @param template - The template string to be parsed and interpolated.
+   * @param variables - An object containing the variables to be used for interpolation.
+   * @returns The interpolated string.
+   */
+  interpolateTemplate(template: string, variables: Record<string, unknown>): string;
+
+  /**
+   * Retrieves and processes a prompt template based on the provided key, LaunchDarkly context, and
+   * variables.
+   *
+   * @param key - A unique identifier for the prompt template. This key is used to fetch the correct
+   *  prompt from storage or configuration.
+   * @param context - The LaunchDarkly context object that contains relevant information about the
+   * current environment, user, or session. This context may influence how the prompt is processed
+   * or personalized.
+   * @param variables - A map of key-value pairs representing dynamic variables to be injected into
+   * the prompt template. The keys correspond to placeholders within the template, and the values
+   * are the corresponding replacements.
+   * @param defaultValue - A fallback value to be used if the prompt template associated with the
+   * key is not found or if any errors occur during processing.
+   *
+   * @returns The processed prompt after all variables have been substituted in the stored prompt
+   * template. If the prompt cannot be retrieved or processed, the `defaultValue` is returned.
+   *
+   * @example
+   * ```
+   * const key = "welcome_prompt";
+   * const context = {...};
+   * const variables = {username: 'john'};
+   * const defaultValue = {};
+   *
+   * const result = modelConfig(key, context, defaultValue, variables);
+   * // Output:
+   * {
+   *   modelId: "gpt-4o",
+   *   temperature: 0.2,
+   *   maxTokens: 4096,
+   *   userDefinedKey: "myValue",
+   *   prompt: [
+   *     {
+   *       role: "system",
+   *       content: "You are an amazing GPT."
+   *     },
+   *     {
+   *       role: "user",
+   *       content: "Explain how you're an amazing GPT."
+   *     }
+   *   ]
+   * }
+   * ```
+   */
+  modelConfig<TDefault extends LDGenerationConfig>(
+    key: string,
+    context: LDContext,
+    defaultValue: TDefault,
+    variables?: Record<string, unknown>,
+  ): Promise<LDAIConfig>;
+}
diff --git a/packages/sdk/server-ai/src/api/config/LDAIConfig.ts b/packages/sdk/server-ai/src/api/config/LDAIConfig.ts
new file mode 100644
index 0000000000..0d47f6eac0
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/config/LDAIConfig.ts
@@ -0,0 +1,64 @@
+import { LDAIConfigTracker } from './LDAIConfigTracker';
+
+/**
+ * Configuration related to the model.
+ */
+export interface LDModelConfig {
+  /**
+   * The ID of the model.
+   */
+  modelId?: string;
+
+  /**
+   * And additional model specific information.
+   */
+  [index: string]: unknown;
+}
+
+/**
+ * Information about prompts.
+ */
+export interface LDMessage {
+  /**
+   * The role of the prompt.
+   */
+  role: 'user' | 'assistant' | 'system';
+  /**
+   * Content for the prompt.
+   */
+  content: string;
+}
+
+/**
+ * Configuration which affects generation.
+ */
+export interface LDGenerationConfig {
+  /**
+   * Optional model configuration.
+   */
+  model?: LDModelConfig;
+  /**
+   * Optional prompt data.
+   */
+  prompt?: LDMessage[];
+}
+
+/**
+ * AI Config value and tracker.
+ */
+export interface LDAIConfig {
+  /**
+   * The result of the AI Config customization.
+   */
+  config: LDGenerationConfig;
+
+  /**
+   * A tracker which can be used to generate analytics.
+   */
+  tracker: LDAIConfigTracker;
+
+  /**
+   * Whether the configuration is enabled.
+   */
+  enabled: boolean;
+}
diff --git a/packages/sdk/server-ai/src/api/config/LDAIConfigTracker.ts b/packages/sdk/server-ai/src/api/config/LDAIConfigTracker.ts
new file mode 100644
index 0000000000..505153f8e3
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/config/LDAIConfigTracker.ts
@@ -0,0 +1,79 @@
+import { LDFeedbackKind, LDTokenUsage } from '../metrics';
+
+/**
+ * The LDAIConfigTracker is used to track various details about AI operations.
+ */
+export interface LDAIConfigTracker {
+  /**
+   * Track the duration of generation.
+   *
+   * Ideally this would not include overhead time such as network communication.
+   *
+   * @param durationMs The duration in milliseconds.
+   */
+  trackDuration(durationMs: number): void;
+
+  /**
+   * Track information about token usage.
+   *
+   * @param tokens Token usage information.
+   */
+  trackTokens(tokens: LDTokenUsage): void;
+
+  /**
+   * Generation was successful.
+   */
+  trackSuccess(): void;
+
+  /**
+   * Track sentiment about the generation.
+   *
+   * @param feedback Feedback about the generation.
+   */
+  trackFeedback(feedback: { kind: LDFeedbackKind }): void;
+
+  /**
+   * Track the duration of execution of the provided function.
+   * @param func The function to track the duration of.
+   * @returns The result of the function.
+   */
+  trackDurationOf(func: () => Promise<any>): Promise<any>;
+
+  /**
+   * Track an OpenAI operation.
+   *
+   * @param func Function which executes the operation.
+   * @returns The result of the operation.
+   */
+  trackOpenAI<
+    TRes extends {
+      usage?: {
+        total_tokens?: number;
+        prompt_tokens?: number;
+        completion_tokens?: number;
+      };
+    },
+  >(
+    func: () => Promise<TRes>,
+  ): Promise<TRes>;
+
+  /**
+   * Track an operation which uses Bedrock.
+   *
+   * @param res The result of the Bedrock operation.
+   * @returns The input operation.
+   */
+  trackBedrockConverse<
+    TRes extends {
+      $metadata: { httpStatusCode?: number };
+      metrics?: { latencyMs?: number };
+      usage?: {
+        inputTokens?: number;
+        outputTokens?: number;
+        totalTokens?: number;
+      };
+    },
+  >(
+    res: TRes,
+  ): TRes;
+}
diff --git a/packages/sdk/server-ai/src/api/config/index.ts b/packages/sdk/server-ai/src/api/config/index.ts
new file mode 100644
index 0000000000..1c07d5c3a4
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/config/index.ts
@@ -0,0 +1,2 @@
+export * from './LDAIConfig';
+export { LDAIConfigTracker } from './LDAIConfigTracker';
diff --git a/packages/sdk/server-ai/src/api/index.ts b/packages/sdk/server-ai/src/api/index.ts
new file mode 100644
index 0000000000..c6c70867bb
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/index.ts
@@ -0,0 +1,3 @@
+export * from './config';
+export * from './metrics';
+export * from './LDAIClient';
diff --git a/packages/sdk/server-ai/src/api/metrics/BedrockTokenUsage.ts b/packages/sdk/server-ai/src/api/metrics/BedrockTokenUsage.ts
new file mode 100644
index 0000000000..0b7fc40e55
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/BedrockTokenUsage.ts
@@ -0,0 +1,13 @@
+import { LDTokenUsage } from './LDTokenUsage';
+
+export function createBedrockTokenUsage(data: {
+  totalTokens?: number;
+  inputTokens?: number;
+  outputTokens?: number;
+}): LDTokenUsage {
+  return {
+    total: data.totalTokens || 0,
+    input: data.inputTokens || 0,
+    output: data.outputTokens || 0,
+  };
+}
diff --git a/packages/sdk/server-ai/src/api/metrics/LDFeedbackKind.ts b/packages/sdk/server-ai/src/api/metrics/LDFeedbackKind.ts
new file mode 100644
index 0000000000..d066241de8
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/LDFeedbackKind.ts
@@ -0,0 +1,13 @@
+/**
+ * Feedback about the generated content.
+ */
+export enum LDFeedbackKind {
+  /**
+   * The sentiment was positive.
+   */
+  Positive = 'positive',
+  /**
+   * The sentiment is negative.
+   */
+  Negative = 'negative',
+}
diff --git a/packages/sdk/server-ai/src/api/metrics/LDTokenUsage.ts b/packages/sdk/server-ai/src/api/metrics/LDTokenUsage.ts
new file mode 100644
index 0000000000..375cbbb625
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/LDTokenUsage.ts
@@ -0,0 +1,19 @@
+/**
+ * Information about token usage.
+ */
+export interface LDTokenUsage {
+  /**
+   * Combined token usage.
+   */
+  total: number;
+
+  /**
+   * Number of tokens in the input.
+   */
+  input: number;
+
+  /**
+   * Number of tokens in the output.
+   */
+  output: number;
+}
diff --git a/packages/sdk/server-ai/src/api/metrics/OpenAiUsage.ts b/packages/sdk/server-ai/src/api/metrics/OpenAiUsage.ts
new file mode 100644
index 0000000000..b2316087e3
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/OpenAiUsage.ts
@@ -0,0 +1,13 @@
+import { LDTokenUsage } from './LDTokenUsage';
+
+export function createOpenAiUsage(data: {
+  total_tokens?: number;
+  prompt_tokens?: number;
+  completion_tokens?: number;
+}): LDTokenUsage {
+  return {
+    total: data.total_tokens ?? 0,
+    input: data.prompt_tokens ?? 0,
+    output: data.completion_tokens ?? 0,
+  };
+}
diff --git a/packages/sdk/server-ai/src/api/metrics/UnderScoreTokenUsage.ts b/packages/sdk/server-ai/src/api/metrics/UnderScoreTokenUsage.ts
new file mode 100644
index 0000000000..201d95aa94
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/UnderScoreTokenUsage.ts
@@ -0,0 +1,9 @@
+import { LDTokenUsage } from './LDTokenUsage';
+
+export function createUnderscoreTokenUsage(data: any): LDTokenUsage {
+  return {
+    total: data.total_tokens || 0,
+    input: data.prompt_tokens || 0,
+    output: data.completion_tokens || 0,
+  };
+}
diff --git a/packages/sdk/server-ai/src/api/metrics/index.ts b/packages/sdk/server-ai/src/api/metrics/index.ts
new file mode 100644
index 0000000000..4bebfd1167
--- /dev/null
+++ b/packages/sdk/server-ai/src/api/metrics/index.ts
@@ -0,0 +1,4 @@
+export * from './BedrockTokenUsage';
+export * from './LDFeedbackKind';
+export * from './LDTokenUsage';
+export * from './UnderScoreTokenUsage';
diff --git a/packages/sdk/server-ai/src/index.ts b/packages/sdk/server-ai/src/index.ts
new file mode 100644
index 0000000000..3f762c5fd0
--- /dev/null
+++ b/packages/sdk/server-ai/src/index.ts
@@ -0,0 +1,14 @@
+import { LDAIClient } from './api/LDAIClient';
+import { LDAIClientImpl } from './LDAIClientImpl';
+import { LDClientMin } from './LDClientMin';
+
+/**
+ * Initialize a new AI client. This client will be used to perform any AI operations.
+ * @param ldClient The base LaunchDarkly client.
+ * @returns A new AI client.
+ */
+export function initAi(ldClient: LDClientMin): LDAIClient {
+  return new LDAIClientImpl(ldClient);
+}
+
+export * from './api';
diff --git a/packages/sdk/server-ai/tsconfig.eslint.json b/packages/sdk/server-ai/tsconfig.eslint.json
new file mode 100644
index 0000000000..56c9b38305
--- /dev/null
+++ b/packages/sdk/server-ai/tsconfig.eslint.json
@@ -0,0 +1,5 @@
+{
+  "extends": "./tsconfig.json",
+  "include": ["/**/*.ts"],
+  "exclude": ["node_modules"]
+}
diff --git a/packages/sdk/server-ai/tsconfig.json b/packages/sdk/server-ai/tsconfig.json
new file mode 100644
index 0000000000..2d1f62a18a
--- /dev/null
+++ b/packages/sdk/server-ai/tsconfig.json
@@ -0,0 +1,21 @@
+{
+  "compilerOptions": {
+    "rootDir": "src",
+    "outDir": "dist",
+    "target": "es2017",
+    "lib": ["es6"],
+    "module": "commonjs",
+    "strict": true,
+    "noImplicitOverride": true,
+    // Needed for CommonJS modules.
+    "allowSyntheticDefaultImports": true,
+    "sourceMap": true,
+    "declaration": true,
+    "declarationMap": true, // enables importers to jump to source
+    "resolveJsonModule": true,
+    "stripInternal": true,
+    "moduleResolution": "node"
+  },
+  "include": ["src"],
+  "exclude": ["**/*.test.ts", "dist", "node_modules", "__tests__"]
+}
diff --git a/packages/sdk/server-ai/tsconfig.ref.json b/packages/sdk/server-ai/tsconfig.ref.json
new file mode 100644
index 0000000000..0c86b2c554
--- /dev/null
+++ b/packages/sdk/server-ai/tsconfig.ref.json
@@ -0,0 +1,7 @@
+{
+  "extends": "./tsconfig.json",
+  "include": ["src/**/*"],
+  "compilerOptions": {
+    "composite": true
+  }
+}
diff --git a/packages/sdk/server-ai/typedoc.json b/packages/sdk/server-ai/typedoc.json
new file mode 100644
index 0000000000..7ac616b544
--- /dev/null
+++ b/packages/sdk/server-ai/typedoc.json
@@ -0,0 +1,5 @@
+{
+  "extends": ["../../../typedoc.base.json"],
+  "entryPoints": ["src/index.ts"],
+  "out": "docs"
+}
diff --git a/release-please-config.json b/release-please-config.json
index 013be3c00b..e19f0a8453 100644
--- a/release-please-config.json
+++ b/release-please-config.json
@@ -31,6 +31,19 @@
     "packages/telemetry/node-server-sdk-otel": {},
     "packages/sdk/browser": {
       "bump-minor-pre-major": true
+    },
+    "packages/sdk/server-ai": {
+      "bump-minor-pre-major": true,
+      "release-as": "0.1.0",
+      "extra-files": [{
+        "type": "json",
+        "path": "examples/bedrock/package.json",
+        "jsonpath": "$.dependencies.@launchdarkly/server-sdk-ai"
+      },{
+        "type": "json",
+        "path": "examples/openai/package.json",
+        "jsonpath": "$.dependencies.@launchdarkly/server-sdk-ai"
+      }]
     }
   },
   "plugins": [
diff --git a/tsconfig.json b/tsconfig.json
index e7ffa9fe3b..0215fb8fb3 100644
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -60,6 +60,9 @@
     },
     {
       "path": "./packages/sdk/browser/contract-tests/entity/tsconfig.ref.json"
+    },
+    {
+      "path": "./packages/sdk/server-ai/tsconfig.ref.json"
     }
   ]
 }