diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index d8be2d4ae6..358a6caa92 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -27,6 +27,7 @@ jobs:
       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'] }}
+      package-server-ai-langchain-released: ${{ steps.release.outputs['packages/ai-providers/server-ai-langchain--release_created'] }}
       package-browser-telemetry-released: ${{ steps.release.outputs['packages/telemetry/browser-telemetry--release_created'] }}
       package-combined-browser-released: ${{ steps.release.outputs['packages/sdk/combined-browser--release_created'] }}
     steps:
@@ -460,3 +461,23 @@ jobs:
         with:
           workspace_path: packages/sdk/combined-browser
           aws_assume_role: ${{ vars.AWS_ROLE_ARN }}
+
+  release-server-ai-langchain:
+    runs-on: ubuntu-latest
+    needs: ['release-please', 'release-server-ai']
+    permissions:
+      id-token: write
+      contents: write
+    if: ${{ always() && !failure() && !cancelled() && needs.release-please.outputs.package-server-ai-langchain-released == 'true'}}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 22.x
+          registry-url: 'https://registry.npmjs.org'
+      - id: release-server-ai-langchain
+        name: Full release of packages/ai-providers/server-ai-langchain
+        uses: ./actions/full-release
+        with:
+          workspace_path: packages/ai-providers/server-ai-langchain
+          aws_assume_role: ${{ vars.AWS_ROLE_ARN }}
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index b19297a489..1dea9a82d7 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,22 +1,23 @@
 {
-  "packages/shared/common": "2.19.0",
-  "packages/shared/sdk-server": "2.16.2",
-  "packages/sdk/server-node": "9.10.2",
+  "packages/ai-providers/server-ai-langchain": "0.0.0",
+  "packages/sdk/akamai-base": "3.0.10",
+  "packages/sdk/akamai-edgekv": "1.4.12",
+  "packages/sdk/browser": "0.8.1",
   "packages/sdk/cloudflare": "2.7.10",
+  "packages/sdk/combined-browser": "0.0.0",
   "packages/sdk/fastly": "0.2.1",
-  "packages/shared/sdk-server-edge": "2.6.9",
+  "packages/sdk/react-native": "10.11.0",
+  "packages/sdk/server-ai": "0.12.0",
+  "packages/sdk/server-node": "9.10.2",
   "packages/sdk/vercel": "1.3.34",
-  "packages/sdk/akamai-base": "3.0.10",
-  "packages/sdk/akamai-edgekv": "1.4.12",
   "packages/shared/akamai-edgeworker-sdk": "2.0.10",
+  "packages/shared/common": "2.19.0",
+  "packages/shared/sdk-client": "1.15.1",
+  "packages/shared/sdk-server": "2.16.2",
+  "packages/shared/sdk-server-edge": "2.6.9",
   "packages/store/node-server-sdk-dynamodb": "6.2.14",
   "packages/store/node-server-sdk-redis": "4.2.14",
-  "packages/shared/sdk-client": "1.15.1",
-  "packages/sdk/react-native": "10.11.0",
-  "packages/telemetry/node-server-sdk-otel": "1.3.2",
-  "packages/sdk/browser": "0.8.1",
-  "packages/sdk/server-ai": "0.12.0",
   "packages/telemetry/browser-telemetry": "1.0.11",
-  "packages/tooling/jest": "0.1.11",
-  "packages/sdk/combined-browser": "0.0.0"
+  "packages/telemetry/node-server-sdk-otel": "1.3.2",
+  "packages/tooling/jest": "0.1.11"
 }
diff --git a/package.json b/package.json
index 313d3cf351..e05ef41e6b 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,7 @@
 {
   "name": "@launchdarkly/js-core",
   "workspaces": [
+    "packages/ai-providers/server-ai-langchain",
     "packages/shared/common",
     "packages/shared/sdk-client",
     "packages/shared/sdk-server",
diff --git a/packages/ai-providers/server-ai-langchain/__tests__/LangChainProvider.test.ts b/packages/ai-providers/server-ai-langchain/__tests__/LangChainProvider.test.ts
new file mode 100644
index 0000000000..5cd7b5879d
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/__tests__/LangChainProvider.test.ts
@@ -0,0 +1,179 @@
+import { AIMessage, HumanMessage, SystemMessage } from '@langchain/core/messages';
+
+import { LangChainProvider } from '../src/LangChainProvider';
+
+// Mock LangChain dependencies
+jest.mock('langchain/chat_models/universal', () => ({
+  initChatModel: jest.fn(),
+}));
+
+// Mock logger
+const mockLogger = {
+  warn: jest.fn(),
+  info: jest.fn(),
+  error: jest.fn(),
+  debug: jest.fn(),
+};
+
+describe('LangChainProvider', () => {
+  describe('convertMessagesToLangChain', () => {
+    it('converts system messages to SystemMessage', () => {
+      const messages = [{ role: 'system' as const, content: 'You are a helpful assistant.' }];
+      const result = LangChainProvider.convertMessagesToLangChain(messages);
+
+      expect(result).toHaveLength(1);
+      expect(result[0]).toBeInstanceOf(SystemMessage);
+      expect(result[0].content).toBe('You are a helpful assistant.');
+    });
+
+    it('converts user messages to HumanMessage', () => {
+      const messages = [{ role: 'user' as const, content: 'Hello, how are you?' }];
+      const result = LangChainProvider.convertMessagesToLangChain(messages);
+
+      expect(result).toHaveLength(1);
+      expect(result[0]).toBeInstanceOf(HumanMessage);
+      expect(result[0].content).toBe('Hello, how are you?');
+    });
+
+    it('converts assistant messages to AIMessage', () => {
+      const messages = [{ role: 'assistant' as const, content: 'I am doing well, thank you!' }];
+      const result = LangChainProvider.convertMessagesToLangChain(messages);
+
+      expect(result).toHaveLength(1);
+      expect(result[0]).toBeInstanceOf(AIMessage);
+      expect(result[0].content).toBe('I am doing well, thank you!');
+    });
+
+    it('converts multiple messages in order', () => {
+      const messages = [
+        { role: 'system' as const, content: 'You are a helpful assistant.' },
+        { role: 'user' as const, content: 'What is the weather like?' },
+        { role: 'assistant' as const, content: 'I cannot check the weather.' },
+      ];
+      const result = LangChainProvider.convertMessagesToLangChain(messages);
+
+      expect(result).toHaveLength(3);
+      expect(result[0]).toBeInstanceOf(SystemMessage);
+      expect(result[1]).toBeInstanceOf(HumanMessage);
+      expect(result[2]).toBeInstanceOf(AIMessage);
+    });
+
+    it('throws error for unsupported message role', () => {
+      const messages = [{ role: 'unknown' as any, content: 'Test message' }];
+
+      expect(() => LangChainProvider.convertMessagesToLangChain(messages)).toThrow(
+        'Unsupported message role: unknown',
+      );
+    });
+
+    it('handles empty message array', () => {
+      const result = LangChainProvider.convertMessagesToLangChain([]);
+
+      expect(result).toHaveLength(0);
+    });
+  });
+
+  describe('createAIMetrics', () => {
+    it('creates metrics with success=true and token usage', () => {
+      const mockResponse = new AIMessage('Test response');
+      mockResponse.response_metadata = {
+        tokenUsage: {
+          totalTokens: 100,
+          promptTokens: 50,
+          completionTokens: 50,
+        },
+      };
+
+      const result = LangChainProvider.createAIMetrics(mockResponse);
+
+      expect(result).toEqual({
+        success: true,
+        usage: {
+          total: 100,
+          input: 50,
+          output: 50,
+        },
+      });
+    });
+
+    it('creates metrics with success=true and no usage when metadata is missing', () => {
+      const mockResponse = new AIMessage('Test response');
+
+      const result = LangChainProvider.createAIMetrics(mockResponse);
+
+      expect(result).toEqual({
+        success: true,
+        usage: undefined,
+      });
+    });
+  });
+
+  describe('invokeModel', () => {
+    let mockLLM: any;
+    let provider: LangChainProvider;
+
+    beforeEach(() => {
+      mockLLM = {
+        invoke: jest.fn(),
+      };
+      provider = new LangChainProvider(mockLLM, mockLogger);
+      jest.clearAllMocks();
+    });
+
+    it('returns success=true for string content', async () => {
+      const mockResponse = new AIMessage('Test response');
+      mockLLM.invoke.mockResolvedValue(mockResponse);
+
+      const messages = [{ role: 'user' as const, content: 'Hello' }];
+      const result = await provider.invokeModel(messages);
+
+      expect(result.metrics.success).toBe(true);
+      expect(result.message.content).toBe('Test response');
+      expect(mockLogger.warn).not.toHaveBeenCalled();
+    });
+
+    it('returns success=false for non-string content and logs warning', async () => {
+      const mockResponse = new AIMessage({ type: 'image', data: 'base64data' } as any);
+      mockLLM.invoke.mockResolvedValue(mockResponse);
+
+      const messages = [{ role: 'user' as const, content: 'Hello' }];
+      const result = await provider.invokeModel(messages);
+
+      expect(result.metrics.success).toBe(false);
+      expect(result.message.content).toBe('');
+      expect(mockLogger.warn).toHaveBeenCalledWith(
+        'Multimodal response not supported, expecting a string. Content type: object, Content:',
+        JSON.stringify({ type: 'image', data: 'base64data' }, null, 2),
+      );
+    });
+
+    it('returns success=false for array content and logs warning', async () => {
+      const mockResponse = new AIMessage(['text', { type: 'image', data: 'base64data' }] as any);
+      mockLLM.invoke.mockResolvedValue(mockResponse);
+
+      const messages = [{ role: 'user' as const, content: 'Hello' }];
+      const result = await provider.invokeModel(messages);
+
+      expect(result.metrics.success).toBe(false);
+      expect(result.message.content).toBe('');
+      expect(mockLogger.warn).toHaveBeenCalledWith(
+        'Multimodal response not supported, expecting a string. Content type: object, Content:',
+        JSON.stringify(['text', { type: 'image', data: 'base64data' }], null, 2),
+      );
+    });
+  });
+
+  describe('mapProvider', () => {
+    it('maps gemini to google-genai', () => {
+      expect(LangChainProvider.mapProvider('gemini')).toBe('google-genai');
+      expect(LangChainProvider.mapProvider('Gemini')).toBe('google-genai');
+      expect(LangChainProvider.mapProvider('GEMINI')).toBe('google-genai');
+    });
+
+    it('returns provider name unchanged for unmapped providers', () => {
+      expect(LangChainProvider.mapProvider('openai')).toBe('openai');
+      expect(LangChainProvider.mapProvider('anthropic')).toBe('anthropic');
+      expect(LangChainProvider.mapProvider('unknown')).toBe('unknown');
+    });
+  });
+});
diff --git a/packages/ai-providers/server-ai-langchain/jest.config.js b/packages/ai-providers/server-ai-langchain/jest.config.js
new file mode 100644
index 0000000000..f106eb3bc9
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/jest.config.js
@@ -0,0 +1,7 @@
+module.exports = {
+  transform: { '^.+\\.ts?$': 'ts-jest' },
+  testMatch: ['**/__tests__/**/*test.ts?(x)'],
+  testEnvironment: 'node',
+  moduleFileExtensions: ['ts', 'tsx', 'js', 'jsx', 'json', 'node'],
+  collectCoverageFrom: ['src/**/*.ts'],
+};
diff --git a/packages/ai-providers/server-ai-langchain/package.json b/packages/ai-providers/server-ai-langchain/package.json
new file mode 100644
index 0000000000..4642fc5e75
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/package.json
@@ -0,0 +1,55 @@
+{
+  "name": "@launchdarkly/server-sdk-ai-langchain",
+  "version": "0.0.0",
+  "description": "LaunchDarkly AI SDK LangChain Provider for Server-Side JavaScript",
+  "homepage": "https://github.com/launchdarkly/js-core/tree/main/packages/ai-providers/server-ai-langchain",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/launchdarkly/js-core.git"
+  },
+  "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": "jest"
+  },
+  "keywords": [
+    "launchdarkly",
+    "ai",
+    "llm",
+    "langchain"
+  ],
+  "author": "LaunchDarkly",
+  "license": "Apache-2.0",
+  "dependencies": {
+    "@langchain/core": ">=0.2.21 <0.3.0",
+    "@launchdarkly/server-sdk-ai": "^0.12.0",
+    "langchain": "^0.2.11"
+  },
+  "devDependencies": {
+    "@launchdarkly/js-server-sdk-common": "2.16.2",
+    "@trivago/prettier-plugin-sort-imports": "^4.1.1",
+    "@types/jest": "^29.5.3",
+    "@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/ai-providers/server-ai-langchain/src/LangChainProvider.ts b/packages/ai-providers/server-ai-langchain/src/LangChainProvider.ts
new file mode 100644
index 0000000000..b7981abac3
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/src/LangChainProvider.ts
@@ -0,0 +1,183 @@
+import { BaseChatModel } from '@langchain/core/language_models/chat_models';
+import { AIMessage, HumanMessage, SystemMessage } from '@langchain/core/messages';
+import { initChatModel } from 'langchain/chat_models/universal';
+
+import { LDLogger } from '@launchdarkly/js-server-sdk-common';
+import {
+  AIProvider,
+  ChatResponse,
+  LDAIConfig,
+  LDAIMetrics,
+  LDMessage,
+  LDTokenUsage,
+} from '@launchdarkly/server-sdk-ai';
+
+/**
+ * LangChain implementation of AIProvider.
+ * This provider integrates LangChain models with LaunchDarkly's tracking capabilities.
+ */
+export class LangChainProvider extends AIProvider {
+  private _llm: BaseChatModel;
+
+  constructor(llm: BaseChatModel, logger?: LDLogger) {
+    super(logger);
+    this._llm = llm;
+  }
+
+  // =============================================================================
+  // MAIN FACTORY METHOD
+  // =============================================================================
+
+  /**
+   * Static factory method to create a LangChain AIProvider from an AI configuration.
+   */
+  static async create(aiConfig: LDAIConfig, logger?: LDLogger): Promise<LangChainProvider> {
+    const llm = await LangChainProvider.createLangChainModel(aiConfig);
+    return new LangChainProvider(llm, logger);
+  }
+
+  // =============================================================================
+  // INSTANCE METHODS (AIProvider Implementation)
+  // =============================================================================
+
+  /**
+   * Invoke the LangChain model with an array of messages.
+   */
+  async invokeModel(messages: LDMessage[]): Promise<ChatResponse> {
+    // Convert LDMessage[] to LangChain messages
+    const langchainMessages = LangChainProvider.convertMessagesToLangChain(messages);
+
+    // Get the LangChain response
+    const response: AIMessage = await this._llm.invoke(langchainMessages);
+
+    // Generate metrics early (assumes success by default)
+    const metrics = LangChainProvider.createAIMetrics(response);
+
+    // Extract text content from the response
+    let content: string = '';
+    if (typeof response.content === 'string') {
+      content = response.content;
+    } else {
+      // Log warning for non-string content (likely multimodal)
+      this.logger?.warn(
+        `Multimodal response not supported, expecting a string. Content type: ${typeof response.content}, Content:`,
+        JSON.stringify(response.content, null, 2),
+      );
+      // Update metrics to reflect content loss
+      metrics.success = false;
+    }
+
+    // Create the assistant message
+    const assistantMessage: LDMessage = {
+      role: 'assistant',
+      content,
+    };
+
+    return {
+      message: assistantMessage,
+      metrics,
+    };
+  }
+
+  /**
+   * Get the underlying LangChain model instance.
+   */
+  getChatModel(): BaseChatModel {
+    return this._llm;
+  }
+
+  // =============================================================================
+  // STATIC UTILITY METHODS
+  // =============================================================================
+
+  /**
+   * Map LaunchDarkly provider names to LangChain provider names.
+   * This method enables seamless integration between LaunchDarkly's standardized
+   * provider naming and LangChain's naming conventions.
+   */
+  static mapProvider(ldProviderName: string): string {
+    const lowercasedName = ldProviderName.toLowerCase();
+
+    const mapping: Record<string, string> = {
+      gemini: 'google-genai',
+    };
+
+    return mapping[lowercasedName] || lowercasedName;
+  }
+
+  /**
+   * Create AI metrics information from a LangChain provider response.
+   * This method extracts token usage information and success status from LangChain responses
+   * and returns a LaunchDarkly AIMetrics object.
+   *
+   * @param langChainResponse The response from the LangChain model
+   * @example
+   * ```typescript
+   * // Use with tracker.trackMetricsOf for automatic tracking
+   * const response = await tracker.trackMetricsOf(
+   *   (result: AIMessage) => LangChainProvider.createAIMetrics(result),
+   *   () => llm.invoke(messages)
+   * );
+   * ```
+   */
+  static createAIMetrics(langChainResponse: AIMessage): LDAIMetrics {
+    // Extract token usage if available
+    let usage: LDTokenUsage | undefined;
+    if (langChainResponse?.response_metadata?.tokenUsage) {
+      const { tokenUsage } = langChainResponse.response_metadata;
+      usage = {
+        total: tokenUsage.totalTokens || 0,
+        input: tokenUsage.promptTokens || 0,
+        output: tokenUsage.completionTokens || 0,
+      };
+    }
+
+    // LangChain responses that complete successfully are considered successful by default
+    return {
+      success: true,
+      usage,
+    };
+  }
+
+  /**
+   * Convert LaunchDarkly messages to LangChain messages.
+   * This helper method enables developers to work directly with LangChain message types
+   * while maintaining compatibility with LaunchDarkly's standardized message format.
+   */
+  static convertMessagesToLangChain(
+    messages: LDMessage[],
+  ): (HumanMessage | SystemMessage | AIMessage)[] {
+    return messages.map((msg) => {
+      switch (msg.role) {
+        case 'system':
+          return new SystemMessage(msg.content);
+        case 'user':
+          return new HumanMessage(msg.content);
+        case 'assistant':
+          return new AIMessage(msg.content);
+        default:
+          throw new Error(`Unsupported message role: ${msg.role}`);
+      }
+    });
+  }
+
+  /**
+   * Create a LangChain model from an AI configuration.
+   * This public helper method enables developers to initialize their own LangChain models
+   * using LaunchDarkly AI configurations.
+   *
+   * @param aiConfig The LaunchDarkly AI configuration
+   * @returns A Promise that resolves to a configured LangChain BaseChatModel
+   */
+  static async createLangChainModel(aiConfig: LDAIConfig): Promise<BaseChatModel> {
+    const modelName = aiConfig.model?.name || '';
+    const provider = aiConfig.provider?.name || '';
+    const parameters = aiConfig.model?.parameters || {};
+
+    // Use LangChain's universal initChatModel to support multiple providers
+    return initChatModel(modelName, {
+      modelProvider: LangChainProvider.mapProvider(provider),
+      ...parameters,
+    });
+  }
+}
diff --git a/packages/ai-providers/server-ai-langchain/src/index.ts b/packages/ai-providers/server-ai-langchain/src/index.ts
new file mode 100644
index 0000000000..63c20c4154
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/src/index.ts
@@ -0,0 +1,10 @@
+/**
+ * This is the API reference for the LaunchDarkly AI SDK LangChain Provider for Server-Side JavaScript.
+ *
+ * This package provides LangChain integration for the LaunchDarkly AI SDK, allowing you to use
+ * LangChain models and chains with LaunchDarkly's tracking and configuration capabilities.
+ *
+ * @packageDocumentation
+ */
+
+export * from './LangChainProvider';
diff --git a/packages/ai-providers/server-ai-langchain/tsconfig.eslint.json b/packages/ai-providers/server-ai-langchain/tsconfig.eslint.json
new file mode 100644
index 0000000000..56c9b38305
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/tsconfig.eslint.json
@@ -0,0 +1,5 @@
+{
+  "extends": "./tsconfig.json",
+  "include": ["/**/*.ts"],
+  "exclude": ["node_modules"]
+}
diff --git a/packages/ai-providers/server-ai-langchain/tsconfig.json b/packages/ai-providers/server-ai-langchain/tsconfig.json
new file mode 100644
index 0000000000..6238d6a0f5
--- /dev/null
+++ b/packages/ai-providers/server-ai-langchain/tsconfig.json
@@ -0,0 +1,20 @@
+{
+  "compilerOptions": {
+    "target": "ES2020",
+    "module": "CommonJS",
+    "lib": ["ES2020"],
+    "moduleResolution": "node",
+    "esModuleInterop": true,
+    "allowSyntheticDefaultImports": true,
+    "strict": true,
+    "skipLibCheck": true,
+    "forceConsistentCasingInFileNames": true,
+    "outDir": "./dist",
+    "rootDir": "./src",
+    "declaration": true,
+    "declarationMap": true,
+    "sourceMap": true
+  },
+  "include": ["src/**/*"],
+  "exclude": ["dist", "node_modules", "**/*.test.ts", "**/*.spec.ts"]
+}
diff --git a/release-please-config.json b/release-please-config.json
index 5f903b99e6..0a0725f91b 100644
--- a/release-please-config.json
+++ b/release-please-config.json
@@ -1,5 +1,9 @@
 {
   "packages": {
+    "packages/ai-providers/server-ai-langchain": {
+      "bump-minor-pre-major": true,
+      "prerelease": true
+    },
     "packages/shared/common": {},
     "packages/shared/sdk-client": {},
     "packages/shared/sdk-server": {},