-[](https://github.com/voltagent/voltagent)
[](https://github.com/voltagent/voltagent/issues)
[](https://github.com/voltagent/voltagent/pulls)
[](https://opensource.org/licenses/MIT)
@@ -35,25 +36,20 @@
-
-**VoltAgent**は、AIエージェントを構築し、オーケストレーションするためのオープンソースTypeScriptフレームワークです。
-メモリ、ワークフロー、ツール、組み込みのLLM可観測性を備えた本番環境対応のエージェントを構築できます。
-
-## なぜVoltAgentなのか？
+
-- **初日から本番環境対応**: インフラをゼロから構築する代わりに、組み込みのメモリ、ワークフロー、可観測性を備えたエージェントをデプロイします。
-- **自信を持ってコーディング**: エージェントシステム全体で型安全なツール、自動推論、コンパイル時の安全性を備えた完全なTypeScriptサポート。
-- **プロのようにデバッグ**: 組み込みのVoltOps可観測性により、すべての決定を追跡し、パフォーマンスを監視し、外部ツールなしでリアルタイムでワークフローを最適化します。
-- **複雑なシステムをシンプルに構築**: プロトタイプから本番環境までスケールする、スーパーバイザーの調整、宣言的ワークフロー、モジュラーアーキテクチャでマルチエージェントチームをオーケストレーションします。
+VoltAgentは、2つの主要な部分で構成されるエンドツーエンドのAIエージェントエンジニアリングプラットフォームです：
-## エージェント開発プラットフォーム
+- **[オープンソースTypeScriptフレームワーク](#core-framework)** – メモリ、RAG、ガードレール、ツール、MCP、音声、ワークフローなど。
+- **[VoltOpsコンソール](#voltops-console)** `クラウド` `セルフホスト` – 可観測性、自動化、デプロイ、評価、ガードレール、プロンプトなど。
-VoltAgentは、2つの補完的なツールを通じてAIエージェントを開発および監視するための完全なプラットフォームを提供します。
+完全なコード制御でエージェントを構築し、本番環境対応の可視性とオペレーションでリリースできます。
-### コアフレームワーク
+
-コアフレームワークを使用すると、任意のAIプロバイダーに接続しながら、メモリ、ツール、複数ステップのワークフローを備えたインテリジェントなエージェントを構築できます。専門化されたエージェントがスーパーバイザーの調整下で連携する洗練されたマルチエージェントシステムを作成します。
+オープンソースフレームワークを使用すると、任意のAIプロバイダーに接続しながら、メモリ、ツール、複数ステップのワークフローを備えたインテリジェントなエージェントを構築できます。専門化されたエージェントがスーパーバイザーの調整下で連携する洗練されたマルチエージェントシステムを作成します。
- **[コアランタイム](https://voltagent.dev/docs/agents/overview/) (`@voltagent/core`)**: 型付きの役割、ツール、メモリ、モデルプロバイダーを1か所で定義し、すべてを整理された状態に保ちます。
- **[ワークフローエンジン](https://voltagent.dev/docs/workflows/overview/)**: カスタム制御フローをつなぎ合わせる代わりに、複数ステップの自動化を宣言的に記述します。
@@ -62,11 +58,10 @@ VoltAgentは、2つの補完的なツールを通じてAIエージェントを
- **[LLM互換性](https://voltagent.dev/docs/getting-started/providers-models/)**: エージェントロジックを書き直さずに、設定を変更するだけでOpenAI、Anthropic、Googleなどのプロバイダー間を切り替えます。
- **[メモリ](https://voltagent.dev/docs/agents/memory/overview/)**: 永続的なメモリアダプターを接続して、エージェントが実行間で重要なコンテキストを記憶できるようにします。
- **[検索とRAG](https://voltagent.dev/docs/rag/overview/)**: データソースから事実を取得し、モデルが回答する前に応答を根拠づける（RAG）レトリーバーエージェントをプラグインします。
-- **[評価](https://voltagent.dev/docs/evals/overview/)**: ワークフローと並行してエージェント評価スイートを実行し、ガードレールをより速く提供します。
-
-### VoltOps LLM可観測性プラットフォーム
-
-VoltAgentには、詳細な実行トレース、パフォーマンスメトリクス、ビジュアルダッシュボードでエージェントをリアルタイムで監視およびデバッグするための組み込みの[VoltOps](#voltopsによる組み込みllm可観測性) LLM可観測性が付属しています。エージェントが行うすべての決定を検査し、ツールの使用を追跡し、組み込みのOpenTelemetryベースの可観測性でワークフローを最適化します。
+- **[VoltAgentナレッジベース](https://voltagent.dev/docs/rag/voltagent/)**: ドキュメントの取り込み、チャンク化、埋め込み、検索のためのマネージドRAGサービスを使用します。
+- **[音声](https://voltagent.dev/docs/agents/voice/)**: OpenAI、ElevenLabs、またはカスタム音声プロバイダーでテキスト読み上げと音声認識機能を追加します。
+- **[ガードレール](https://voltagent.dev/docs/guardrails/overview/)**: 実行時にエージェントの入力または出力を傍受して検証し、コンテンツポリシーと安全ルールを適用します。
+- **[評価](https://voltagent.dev/docs/evals/overview/)**: ワークフローと並行してエージェント評価スイートを実行し、エージェントの動作を測定および改善します。
#### MCPサーバー (@voltagent/mcp-docs-server)
@@ -154,7 +149,7 @@ Test your agents with VoltOps Console: https://console.voltagent.dev
4. チャットを開始：エージェント詳細ページで、右下のチャットアイコンをクリックしてチャットウィンドウを開きます。
5. メッセージを送信：「こんにちは」のようなメッセージを入力してEnterキーを押します。
-
+[](https://github.com/user-attachments/assets/26340c6a-be34-48a5-9006-e822bf6098a7)
### 最初のワークフローの実行
@@ -235,7 +230,7 @@ export const expenseApprovalWorkflow = createWorkflowChain({
VoltOpsコンソールから直接、事前構築された`expenseApprovalWorkflow`をテストできます：
-
+[](https://github.com/user-attachments/assets/3d3ea67b-4ab5-4dc0-932d-cedd92894b18)
1. **ワークフローページに移動**：サーバーを起動した後、[ワークフローページ](https://console.voltagent.dev/workflows)に直接移動します。
2. **プロジェクトを選択**：プロジェクトセレクターを使用してプロジェクトを選択します（例：「my-agent-app」）。
@@ -251,9 +246,22 @@ VoltOpsコンソールから直接、事前構築された`expenseApprovalWorkfl
```
5. **結果を表示**：実行後、各ステップの詳細なログを検査し、コンソールで直接最終出力を確認できます。
-## VoltOpsによる組み込みLLM可観測性
+## サンプル
-VoltAgentには、エージェントをリアルタイムで監視、デバッグ、最適化するのに役立つ組み込みのLLM可観測性プラットフォームであるVoltOpsが付属しています。
+より多くのサンプルについては、[サンプルリポジトリ](https://github.com/VoltAgent/voltagent/tree/main/examples)をご覧ください。
+
+- **[Airtableエージェント](https://voltagent.dev/examples/guides/airtable-agent)** - 新しいレコードに反応し、VoltOpsアクションでAirtableに更新を書き戻します。
+- **[Slackエージェント](https://voltagent.dev/examples/guides/slack-agent)** - チャンネルメッセージに応答し、VoltOps Slackアクションで返信します。
+- **[ChatGPTアプリとVoltAgent](https://voltagent.dev/examples/agents/chatgpt-app)** - VoltAgentをMCP経由でデプロイし、ChatGPTアプリに接続します。
+- **[WhatsApp注文エージェント](https://voltagent.dev/examples/agents/whatsapp-ai-agent)** - 自然な会話で食品注文を処理するWhatsAppチャットボットを構築します。（[ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-whatsapp)）
+- **[YouTubeからブログエージェント](https://voltagent.dev/examples/agents/youtube-blog-agent)** - MCPツールを使用したスーパーバイザーエージェントでYouTube動画をMarkdownブログ投稿に変換します。（[ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-youtube-to-blog)）
+- **[AI広告生成エージェント](https://voltagent.dev/examples/agents/ai-instagram-ad-agent)** - BrowserBase StagehandとGoogle Gemini AIを使用してInstagram広告を生成します。（[ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-ad-creator)）
+- **[AIレシピ生成エージェント](https://voltagent.dev/examples/agents/recipe-generator)** - 材料と好みに基づいてパーソナライズされた料理提案を作成します。（[ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-recipe-generator) | [ビデオ](https://youtu.be/KjV1c6AhlfY)）
+- **[AI研究アシスタントエージェント](https://voltagent.dev/examples/agents/research-assistant)** - 包括的なレポートを生成するマルチエージェント研究ワークフロー。（[ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-research-assistant) | [ビデオ](https://youtu.be/j6KAUaoZMy4)）
+
+
+
+VoltOpsコンソールは、VoltAgentのプラットフォーム側であり、可観測性、自動化、デプロイを提供し、リアルタイムの実行トレース、パフォーマンスメトリクス、ビジュアルダッシュボードで本番環境のエージェントを監視およびデバッグできます。
🎬 [ライブデモを試す](https://console.voltagent.dev/demo)
@@ -265,22 +273,17 @@ VoltAgentには、エージェントをリアルタイムで監視、デバッ
詳細なトレースとパフォーマンスメトリクスでエージェントの実行フローを深く掘り下げます。
-
-
-
+
@@ -288,132 +291,63 @@ VoltAgentには、エージェントをリアルタイムで監視、デバッ
エージェントのメモリ、コンテキスト、会話履歴を検査および管理します。
-
-
### トレース
エージェントの動作を理解し、パフォーマンスを最適化するために完全な実行トレースを分析します。
-
-
### プロンプトビルダー
コンソールで直接プロンプトを設計、テスト、改良します。
-
-
-
-
-## 例
-
-完全なソースコードとビデオチュートリアルを備えたVoltAgentの実世界の実装を探索します。
-
-より多くの例とユースケースについては、[例のリポジトリ](https://github.com/VoltAgent/voltagent/tree/main/examples)をご覧ください。
-
-### WhatsApp注文エージェント
-
-自然な会話を通じて食品注文を処理し、データベースからメニュー項目を管理し、完全な会話コンテキストで注文を処理するWhatsAppチャットボットを構築します。
-
-
+### デプロイ
-- 📖 [チュートリアル](https://voltagent.dev/examples/agents/whatsapp-ai-agent)
-- 💻 [ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-whatsapp)
+ワンクリックのGitHub統合とマネージドインフラストラクチャでエージェントを本番環境にデプロイします。
-### YouTube to ブログエージェント
+
-MCPツール、共有ワーキングメモリ、VoltOps可観測性を備えたサブエージェントを調整するスーパーバイザーエージェントを使用して、YouTube動画をMarkdownブログ投稿に変換します。
+📖 [VoltOpsデプロイドキュメント](https://voltagent.dev/docs/deployment/voltops/)
-
-- 📖 [チュートリアル](https://voltagent.dev/examples/agents/youtube-blog-agent)
-- 💻 [ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-youtube-to-blog)
+### モニタリング
-### AI広告生成エージェント
+システム全体のエージェントの健全性、パフォーマンスメトリクス、リソース使用量を監視します。
-BrowserBase Stagehandを使用してランディングページを分析し、ブランドデータを抽出し、Google Gemini AIを通じてビジュアルを生成するInstagram広告ジェネレーターを実装します。
+
-- 📖 [チュートリアル](https://voltagent.dev/examples/agents/ai-instagram-ad-agent)
-- 💻 [ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-ad-creator)
+### 評価
-### AIレシピ生成エージェント
+ベンチマークに対してエージェントの動作、精度、パフォーマンスをテストする評価スイートを実行します。
-利用可能な材料、食事の好み、時間制約に基づいてパーソナライズされた料理提案を作成するインテリジェントなレシピ推奨システムを構築します。
+
+組み込みの検索拡張生成機能でエージェントをナレッジソースに接続します。
-- 📖 [チュートリアル](https://voltagent.dev/examples/agents/recipe-generator)
-- 📹 [ビデオを見る](https://youtu.be/KjV1c6AhlfY)
-- 💻 [ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-recipe-generator)
-
-### AI研究アシスタントエージェント
-
-型安全なデータフローでトピックを研究し、包括的なレポートを生成するために、さまざまなAIエージェントが協力するマルチエージェント研究ワークフローを作成します。
-
-
-
-- 📖 [チュートリアル](https://voltagent.dev/examples/agents/research-assistant)
-- 📹 [ビデオを見る](https://youtu.be/j6KAUaoZMy4)
-- 💻 [ソースコード](https://github.com/VoltAgent/voltagent/tree/main/examples/with-research-assistant)
-
-## ユースケース
-
-さまざまな業界の実際のビジネスニーズに対応するAIエージェントを構築します：
-
-- **[HRエージェント](https://voltagent.dev/use-cases/hr-agent/)** - 採用、従業員のオンボーディング、HRサポートタスクを自動化します。
-- **[カスタマーサポートエージェント](https://voltagent.dev/use-cases/customer-support-agent/)** - 顧客の質問や問題を処理するサポートエージェントを構築します。
-- **[営業チーム](https://voltagent.dev/use-cases/sales-teams/)** - リードを検証し、顧客データを収集し、営業アウトリーチをパーソナライズします。
-- **[財務エージェント](https://voltagent.dev/use-cases/finance-agent/)** - 請求書を管理し、経費を追跡し、財務報告書を生成します。
-- **[開発エージェント](https://voltagent.dev/use-cases/development-agent/)** - コードをレビューし、デプロイを管理し、開発チームを支援します。
-- **[マーケティングエージェント](https://voltagent.dev/use-cases/marketing-agent/)** - キャンペーンを計画し、コンテンツを作成し、マーケティングパフォーマンスを分析します。
-- **[法務エージェント](https://voltagent.dev/use-cases/legal-agent/)** - 契約をレビューし、コンプライアンスを確認し、法的タスクを処理します。
-- **[保険エージェント](https://voltagent.dev/use-cases/insurance-agent/)** - 請求を処理し、リスクを評価し、ポリシーを管理します。
-- **[産業エージェント](https://voltagent.dev/use-cases/industrial-agent/)** - 機器を監視し、メンテナンスニーズを予測し、安全性を確保します。
-- **[教育エージェント](https://voltagent.dev/use-cases/education-agent/)** - パーソナライズされた指導を提供し、学生の進捗を追跡し、学習をサポートします。
-- **[政府エージェント](https://voltagent.dev/use-cases/government-agent/)** - 許可申請を処理し、給付金を処理し、市民にサービスを提供します。
-- **[ドキュメントエージェント](https://voltagent.dev/use-cases/documentation-agent/)** - APIドキュメントを作成し、変更ログを書き、コードからチュートリアルを生成します。
+
## VoltAgentを学ぶ
-- 📖 **[インタラクティブチュートリアルから始める](https://voltagent.dev/tutorial/introduction/)**ことで、AIエージェント構築の基礎を学びます。
+- **[インタラクティブチュートリアルから始める](https://voltagent.dev/tutorial/introduction/)** ことで、AIエージェント構築の基礎を学びます。
- **[ドキュメント](https://voltagent.dev/docs/)**: ガイド、概念、チュートリアルを深く掘り下げます。
-- **[例](https://github.com/voltagent/voltagent/tree/main/examples)**: 実用的な実装を探索します。
+- **[サンプル](https://github.com/voltagent/voltagent/tree/main/examples)**: 実用的な実装を探索します。
- **[ブログ](https://voltagent.dev/blog/)**: 技術的な洞察とベストプラクティスについて詳しく読みます。
## 貢献
@@ -426,10 +360,8 @@ BrowserBase Stagehandを使用してランディングページを分析し、
VoltAgentはコミュニティの努力であり、あなたのような人々のおかげで継続的に改善されています。
-
-
-あなたのスターは、より多くの開発者にリーチするのに役立ちます！VoltAgentが役立つと思ったら、プロジェクトをサポートし、他の人が発見できるようにGitHubでスターを付けることを検討してください。
+
## ライセンス
-MITライセンスの下でライセンスされています、Copyright © 2025-present VoltAgent.
+MITライセンスの下でライセンスされています、Copyright © 2026-present VoltAgent.
diff --git a/i18n/README-kr.md b/i18n/README-kr.md
index bc4cbf0f8..da30db6bb 100644
--- a/i18n/README-kr.md
+++ b/i18n/README-kr.md
@@ -1,10 +1,12 @@
-
+
-
-
+
+AI 에이전트 엔지니어링 플랫폼
+
+
@@ -22,7 +24,6 @@
-[](https://github.com/voltagent/voltagent)
[](https://github.com/voltagent/voltagent/issues)
[](https://github.com/voltagent/voltagent/pulls)
[](https://opensource.org/licenses/MIT)
@@ -35,25 +36,20 @@
-
-
-**VoltAgent**는 AI 에이전트를 구축하고 오케스트레이션하기 위한 오픈 소스 TypeScript 프레임워크입니다.
-메모리, 워크플로, 도구, 그리고 내장된 LLM 관찰 가능성을 갖춘 프로덕션급 에이전트를 구축할 수 있습니다.
-
-## 왜 VoltAgent인가요?
+
+⭐ 마음에 드시면 스타를 눌러주세요 ⬆️
+
-- **첫날부터 프로덕션 준비**: 인프라를 처음부터 구축하는 대신 내장 메모리, 워크플로, 관찰 가능성을 갖춘 에이전트를 배포하세요.
-- **자신감 있게 코딩**: 전체 에이전트 시스템에서 타입 안전 도구, 자동 추론, 컴파일 타임 안전성을 갖춘 완전한 TypeScript 지원.
-- **프로처럼 디버그**: 내장 VoltOps 관찰 가능성으로 모든 결정을 추적하고, 성능을 모니터링하며, 외부 도구 없이 실시간으로 워크플로를 최적화하세요.
-- **복잡한 시스템을 간단하게 구축**: 프로토타입에서 프로덕션까지 확장되는 감독자 조정, 선언적 워크플로, 모듈식 아키텍처로 멀티 에이전트 팀을 오케스트레이션하세요.
+VoltAgent는 두 가지 주요 부분으로 구성된 엔드투엔드 AI 에이전트 엔지니어링 플랫폼입니다:
-## 에이전트 개발 플랫폼
+- **[오픈소스 TypeScript 프레임워크](#core-framework)** – 메모리, RAG, 가드레일, 도구, MCP, 음성, 워크플로 등.
+- **[VoltOps 콘솔](#voltops-console)** `클라우드` `셀프 호스팅` – 관찰 가능성, 자동화, 배포, 평가, 가드레일, 프롬프트 등.
-VoltAgent는 두 가지 보완적인 도구를 통해 AI 에이전트를 개발하고 모니터링하기 위한 완전한 플랫폼을 제공합니다.
+완전한 코드 제어로 에이전트를 구축하고 프로덕션 준비된 가시성과 운영으로 출시하세요.
-### 코어 프레임워크
+
코어 TypeScript 프레임워크
-코어 프레임워크를 사용하면 모든 AI 제공자에 연결하면서 메모리, 도구, 다단계 워크플로를 갖춘 지능형 에이전트를 구축할 수 있습니다. 전문화된 에이전트가 감독자 조정 하에 함께 작동하는 정교한 멀티 에이전트 시스템을 만드세요.
+오픈소스 프레임워크를 사용하면 모든 AI 제공자에 연결하면서 메모리, 도구, 다단계 워크플로를 갖춘 지능형 에이전트를 구축할 수 있습니다. 전문화된 에이전트가 감독자 조정 하에 함께 작동하는 정교한 멀티 에이전트 시스템을 만드세요.
- **[코어 런타임](https://voltagent.dev/docs/agents/overview/) (`@voltagent/core`)**: 타입이 지정된 역할, 도구, 메모리, 모델 제공자를 한 곳에 정의하여 모든 것을 체계적으로 유지하세요.
- **[워크플로 엔진](https://voltagent.dev/docs/workflows/overview/)**: 커스텀 제어 흐름을 연결하는 대신 다단계 자동화를 선언적으로 설명하세요.
@@ -62,11 +58,10 @@ VoltAgent는 두 가지 보완적인 도구를 통해 AI 에이전트를 개발
- **[LLM 호환성](https://voltagent.dev/docs/getting-started/providers-models/)**: 에이전트 로직을 다시 작성하지 않고 구성을 변경하여 OpenAI, Anthropic, Google 또는 다른 제공자 간 전환하세요.
- **[메모리](https://voltagent.dev/docs/agents/memory/overview/)**: 내구성 있는 메모리 어댑터를 연결하여 에이전트가 실행 간 중요한 컨텍스트를 기억하도록 하세요.
- **[검색 & RAG](https://voltagent.dev/docs/rag/overview/)**: 데이터 소스에서 사실을 가져오고 모델이 답변하기 전에 응답을 기반으로 하는(RAG) 검색기 에이전트를 연결하세요.
-- **[평가](https://voltagent.dev/docs/evals/overview/)**: 워크플로와 함께 에이전트 평가 스위트를 실행하여 가드레일을 더 빠르게 제공하세요.
-
-### VoltOps LLM 관찰 가능성 플랫폼
-
-VoltAgent는 상세한 실행 추적, 성능 메트릭, 시각적 대시보드로 에이전트를 실시간으로 모니터링하고 디버그하기 위한 내장 [VoltOps](#built-in-llm-observability-with-voltops) LLM 관찰 가능성과 함께 제공됩니다. 에이전트가 내리는 모든 결정을 검사하고, 도구 사용을 추적하며, 내장 OpenTelemetry 기반 관찰 가능성으로 워크플로를 최적화하세요.
+- **[VoltAgent 지식 베이스](https://voltagent.dev/docs/rag/voltagent/)**: 문서 수집, 청킹, 임베딩, 검색을 위한 매니지드 RAG 서비스를 사용하세요.
+- **[음성](https://voltagent.dev/docs/agents/voice/)**: OpenAI, ElevenLabs 또는 커스텀 음성 제공자로 텍스트 음성 변환 및 음성 텍스트 변환 기능을 추가하세요.
+- **[가드레일](https://voltagent.dev/docs/guardrails/overview/)**: 런타임에 에이전트 입력 또는 출력을 가로채고 검증하여 콘텐츠 정책 및 안전 규칙을 적용하세요.
+- **[평가](https://voltagent.dev/docs/evals/overview/)**: 워크플로와 함께 에이전트 평가 스위트를 실행하여 에이전트 동작을 측정하고 개선하세요.
#### MCP 서버 (@voltagent/mcp-docs-server)
@@ -154,7 +149,7 @@ Test your agents with VoltOps Console: https://console.voltagent.dev
4. 채팅 시작: 에이전트 세부정보 페이지에서 오른쪽 하단의 채팅 아이콘을 클릭하여 채팅 창을 엽니다.
5. 메시지 보내기: "안녕하세요"와 같은 메시지를 입력하고 Enter를 누르세요.
-
+[](https://github.com/user-attachments/assets/26340c6a-be34-48a5-9006-e822bf6098a7)
### 첫 번째 워크플로 실행하기
@@ -235,7 +230,7 @@ export const expenseApprovalWorkflow = createWorkflowChain({
VoltOps 콘솔에서 직접 사전 구축된 `expenseApprovalWorkflow`를 테스트할 수 있습니다:
-
+[](https://github.com/user-attachments/assets/3d3ea67b-4ab5-4dc0-932d-cedd92894b18)
1. **워크플로 페이지로 이동**: 서버를 시작한 후 [워크플로 페이지](https://console.voltagent.dev/workflows)로 직접 이동하세요.
2. **프로젝트 선택**: 프로젝트 선택기를 사용하여 프로젝트를 선택하세요(예: "my-agent-app").
@@ -251,9 +246,22 @@ VoltOps 콘솔에서 직접 사전 구축된 `expenseApprovalWorkflow`를 테스
```
5. **결과 보기**: 실행 후 각 단계에 대한 상세 로그를 검사하고 콘솔에서 직접 최종 출력을 볼 수 있습니다.
-## VoltOps를 통한 내장 LLM 관찰 가능성
+## 예제
+
+더 많은 예제는 [예제 리포지토리](https://github.com/VoltAgent/voltagent/tree/main/examples)를 방문하세요.
+
+- **[Airtable 에이전트](https://voltagent.dev/examples/guides/airtable-agent)** - 새 레코드에 반응하고 VoltOps 액션으로 Airtable에 업데이트를 작성합니다.
+- **[Slack 에이전트](https://voltagent.dev/examples/guides/slack-agent)** - 채널 메시지에 응답하고 VoltOps Slack 액션으로 답장합니다.
+- **[ChatGPT 앱과 VoltAgent](https://voltagent.dev/examples/agents/chatgpt-app)** - VoltAgent를 MCP를 통해 배포하고 ChatGPT 앱에 연결합니다.
+- **[WhatsApp 주문 에이전트](https://voltagent.dev/examples/agents/whatsapp-ai-agent)** - 자연스러운 대화로 음식 주문을 처리하는 WhatsApp 챗봇을 구축합니다. ([소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-whatsapp))
+- **[YouTube to 블로그 에이전트](https://voltagent.dev/examples/agents/youtube-blog-agent)** - MCP 도구를 사용한 감독자 에이전트로 YouTube 비디오를 Markdown 블로그 게시물로 변환합니다. ([소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-youtube-to-blog))
+- **[AI 광고 생성 에이전트](https://voltagent.dev/examples/agents/ai-instagram-ad-agent)** - BrowserBase Stagehand와 Google Gemini AI를 사용하여 Instagram 광고를 생성합니다. ([소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-ad-creator))
+- **[AI 레시피 생성 에이전트](https://voltagent.dev/examples/agents/recipe-generator)** - 재료와 선호도에 따라 개인화된 요리 제안을 만듭니다. ([소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-recipe-generator) | [비디오](https://youtu.be/KjV1c6AhlfY))
+- **[AI 연구 어시스턴트 에이전트](https://voltagent.dev/examples/agents/research-assistant)** - 포괄적인 보고서를 생성하는 멀티 에이전트 연구 워크플로. ([소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-research-assistant) | [비디오](https://youtu.be/j6KAUaoZMy4))
+
+
VoltOps 콘솔: LLM 관찰 가능성 - 자동화 - 배포
-VoltAgent는 에이전트를 실시간으로 모니터링, 디버그 및 최적화하는 데 도움이 되는 내장 LLM 관찰 가능성 플랫폼인 VoltOps와 함께 제공됩니다.
+VoltOps 콘솔은 VoltAgent의 플랫폼 측면으로, 관찰 가능성, 자동화, 배포를 제공하여 실시간 실행 추적, 성능 메트릭, 시각적 대시보드로 프로덕션 에이전트를 모니터링하고 디버그할 수 있습니다.
🎬 [라이브 데모 체험](https://console.voltagent.dev/demo)
@@ -265,22 +273,17 @@ VoltAgent는 에이전트를 실시간으로 모니터링, 디버그 및 최적
상세한 추적 및 성능 메트릭으로 에이전트 실행 흐름을 깊이 있게 살펴보세요.
-
-
-
+
### 대시보드
모든 에이전트, 워크플로 및 시스템 성능 메트릭에 대한 포괄적인 개요를 얻으세요.
-
-
-
+
### 로그
모든 에이전트 상호작용 및 워크플로 단계에 대한 상세한 실행 로그를 추적하세요.
-
@@ -288,130 +291,61 @@ VoltAgent는 에이전트를 실시간으로 모니터링, 디버그 및 최적
에이전트 메모리, 컨텍스트 및 대화 기록을 검사하고 관리하세요.
-
-
### 추적
에이전트 동작을 이해하고 성능을 최적화하기 위해 완전한 실행 추적을 분석하세요.
-
-
### 프롬프트 빌더
콘솔에서 직접 프롬프트를 설계, 테스트 및 개선하세요.
-
-
-
-
-## 예제
-
-완전한 소스 코드 및 비디오 튜토리얼과 함께 VoltAgent의 실제 구현을 탐색하세요.
-
-더 많은 예제 및 사용 사례는 [예제 리포지토리](https://github.com/VoltAgent/voltagent/tree/main/examples)를 방문하세요.
-
-### WhatsApp 주문 에이전트
-
-자연스러운 대화를 통해 음식 주문을 처리하고, 데이터베이스에서 메뉴 항목을 관리하며, 완전한 대화 컨텍스트로 주문을 처리하는 WhatsApp 챗봇을 구축하세요.
-
-
-
-
-
-
-
-
-- 📖 [튜토리얼](https://voltagent.dev/examples/agents/whatsapp-ai-agent)
-- 💻 [소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-whatsapp)
-
-### YouTube to 블로그 에이전트
-
-MCP 도구, 공유 작업 메모리 및 VoltOps 관찰 가능성을 갖춘 서브 에이전트를 조정하는 감독자 에이전트를 사용하여 YouTube 비디오를 Markdown 블로그 게시물로 변환하세요.
-
-
-
-
-
-
-
-
-- 📖 [튜토리얼](https://voltagent.dev/examples/agents/youtube-blog-agent)
-- 💻 [소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-youtube-to-blog)
+
-### AI 광고 생성 에이전트
+### 배포
-BrowserBase Stagehand를 사용하여 랜딩 페이지를 분석하고, 브랜드 데이터를 추출하며, Google Gemini AI를 통해 비주얼을 생성하는 Instagram 광고 생성기를 구현하세요.
+원클릭 GitHub 통합 및 매니지드 인프라로 에이전트를 프로덕션에 배포하세요.
-
+
-
-
-
+📖 [VoltOps 배포 문서](https://voltagent.dev/docs/deployment/voltops/)
-
-
+### 트리거 & 액션
-- 📖 [튜토리얼](https://voltagent.dev/examples/agents/ai-instagram-ad-agent)
-- 💻 [소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-ad-creator)
+웹훅, 스케줄, 커스텀 트리거로 에이전트 워크플로를 자동화하여 외부 이벤트에 반응하세요.
-### AI 레시피 생성 에이전트
+
-사용 가능한 재료, 식단 선호도 및 시간 제약을 기반으로 개인화된 요리 제안을 생성하는 지능형 레시피 추천 시스템을 구축하세요.
+### 모니터링
-
+전체 시스템에서 에이전트 상태, 성능 메트릭 및 리소스 사용량을 모니터링하세요.
-
-
-
+
-
-
+### 가드레일
-- 📖 [튜토리얼](https://voltagent.dev/examples/agents/recipe-generator)
-- 📹 [비디오 시청](https://youtu.be/KjV1c6AhlfY)
-- 💻 [소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-recipe-generator)
+에이전트가 정의된 매개변수 내에서 작동하도록 안전 경계 및 콘텐츠 필터를 설정하세요.
-### AI 연구 어시스턴트 에이전트
+
-타입 안전 데이터 흐름으로 주제를 연구하고 포괄적인 보고서를 생성하기 위해 다양한 AI 에이전트가 협업하는 멀티 에이전트 연구 워크플로를 생성하세요.
+### 평가
-
+벤치마크에 대해 에이전트 동작, 정확도 및 성능을 테스트하는 평가 스위트를 실행하세요.
-
-
-
+
-
-
+### RAG (지식 베이스)
-- 📖 [튜토리얼](https://voltagent.dev/examples/agents/research-assistant)
-- 📹 [비디오 시청](https://youtu.be/j6KAUaoZMy4)
-- 💻 [소스 코드](https://github.com/VoltAgent/voltagent/tree/main/examples/with-research-assistant)
+내장된 검색 증강 생성 기능으로 에이전트를 지식 소스에 연결하세요.
-## 사용 사례
-
-다양한 산업 전반의 실제 비즈니스 요구 사항을 위한 AI 에이전트를 구축하세요:
-
-- **[HR 에이전트](https://voltagent.dev/use-cases/hr-agent/)** - 채용, 직원 온보딩 및 HR 지원 작업을 자동화합니다.
-- **[고객 지원 에이전트](https://voltagent.dev/use-cases/customer-support-agent/)** - 고객 질문 및 문제를 처리하는 지원 에이전트를 구축합니다.
-- **[영업 팀](https://voltagent.dev/use-cases/sales-teams/)** - 리드를 검증하고, 고객 데이터를 수집하며, 영업 아웃리치를 개인화합니다.
-- **[재무 에이전트](https://voltagent.dev/use-cases/finance-agent/)** - 송장을 관리하고, 비용을 추적하며, 재무 보고서를 생성합니다.
-- **[개발 에이전트](https://voltagent.dev/use-cases/development-agent/)** - 코드를 검토하고, 배포를 관리하며, 개발 팀을 지원합니다.
-- **[마케팅 에이전트](https://voltagent.dev/use-cases/marketing-agent/)** - 캠페인을 계획하고, 콘텐츠를 생성하며, 마케팅 성과를 분석합니다.
-- **[법률 에이전트](https://voltagent.dev/use-cases/legal-agent/)** - 계약을 검토하고, 규정 준수를 확인하며, 법률 작업을 처리합니다.
-- **[보험 에이전트](https://voltagent.dev/use-cases/insurance-agent/)** - 청구를 처리하고, 위험을 평가하며, 정책을 관리합니다.
-- **[산업 에이전트](https://voltagent.dev/use-cases/industrial-agent/)** - 장비를 모니터링하고, 유지 보수 필요를 예측하며, 안전을 보장합니다.
-- **[교육 에이전트](https://voltagent.dev/use-cases/education-agent/)** - 개인화된 튜터링을 제공하고, 학생 진행 상황을 추적하며, 학습을 지원합니다.
-- **[정부 에이전트](https://voltagent.dev/use-cases/government-agent/)** - 허가 신청을 처리하고, 혜택을 처리하며, 시민을 서비스합니다.
-- **[문서화 에이전트](https://voltagent.dev/use-cases/documentation-agent/)** - API 문서를 생성하고, 변경 로그를 작성하며, 코드에서 튜토리얼을 생성합니다.
+
## VoltAgent 학습하기
-- 📖 **[대화형 튜토리얼로 시작](https://voltagent.dev/tutorial/introduction/)**하여 AI 에이전트 구축의 기본을 배우세요.
+- **[대화형 튜토리얼로 시작](https://voltagent.dev/tutorial/introduction/)**하여 AI 에이전트 구축의 기본을 배우세요.
- **[문서](https://voltagent.dev/docs/)**: 가이드, 개념 및 튜토리얼을 깊이 있게 살펴보세요.
- **[예제](https://github.com/voltagent/voltagent/tree/main/examples)**: 실용적인 구현을 탐색하세요.
- **[블로그](https://voltagent.dev/blog/)**: 기술적 통찰력 및 모범 사례에 대해 더 읽어보세요.
@@ -426,10 +360,8 @@ BrowserBase Stagehand를 사용하여 랜딩 페이지를 분석하고, 브랜
VoltAgent는 커뮤니티의 노력이며, 여러분과 같은 사람들 덕분에 계속해서 더 나아지고 있습니다.
-
-
-여러분의 스타는 더 많은 개발자에게 다가가는 데 도움이 됩니다! VoltAgent가 유용하다고 생각하신다면, 프로젝트를 지원하고 다른 사람들이 발견할 수 있도록 GitHub에서 스타를 주는 것을 고려해주세요.
+
## 라이선스
-MIT 라이선스 하에 라이선스가 부여됩니다, Copyright © 2025-present VoltAgent.
+MIT 라이선스 하에 라이선스가 부여됩니다, Copyright © 2026-present VoltAgent.
diff --git a/packages/core/README.md b/packages/core/README.md
index 3381b72e5..4ef78b06f 100644
--- a/packages/core/README.md
+++ b/packages/core/README.md
@@ -1,86 +1,63 @@
-
+
-
-
+
+AI Agent Engineering Platform
+
-
- VoltAgent is an open source TypeScript framework for building and orchestrating AI agents.
-Escape the limitations of no-code builders and the complexity of starting from scratch.
-
-
-
-
-[](https://www.npmjs.com/package/@voltagent/core)
+[](https://github.com/voltagent/voltagent/issues)
+[](https://github.com/voltagent/voltagent/pulls)
+[](https://opensource.org/licenses/MIT)
[](CODE_OF_CONDUCT.md)
+[](https://www.npmjs.com/package/@voltagent/core)
+
+[](https://www.npmjs.com/package/@voltagent/core)
[](https://s.voltagent.dev/discord)
[](https://twitter.com/voltagent_dev)
-
-
-
-
-## What is VoltAgent?
-
-> An **AI Agent Framework** provides the foundational structure and tools needed to build applications powered by autonomous agents. These agents, often driven by Large Language Models (LLMs), can perceive their environment, make decisions, and take actions to achieve specific goals. Building such agents from scratch involves managing complex interactions with LLMs, handling state, connecting to external tools and data, and orchestrating workflows.
-
-**VoltAgent** is an open-source TypeScript framework that acts as this essential toolkit. It simplifies the development of AI agent applications by providing modular building blocks, standardized patterns, and abstractions. Whether you're creating chatbots, virtual assistants, automated workflows, or complex multi-agent systems, VoltAgent handles the underlying complexity, allowing you to focus on defining your agents' capabilities and logic.
+VoltAgent is an end-to-end AI Agent Engineering Platform that consists of two main parts:
-Instead of building everything from scratch, VoltAgent provides ready-made, modular building blocks:
+- **[Open-Source TypeScript Framework](#core-framework)** – Memory, RAG, Guardrails, Tools, MCP, Voice, Workflow, and more.
+- **[VoltOps Console](#voltops-console)** `Cloud` `Self-Hosted` – Observability, Automation, Deployment, Evals, Guardrails, Prompts, and more.
-- **Core Engine (`@voltagent/core`)**: The heart of VoltAgent, providing fundamental capabilities for your AI agents Define individual agents with specific roles, tools, and memory.
-- **Multi-Agent Systems**: Architect complex applications by coordinating multiple specialized agents using Supervisors.
-- **Workflow Engine**: Go beyond simple request-response. Orchestrate multi-step automations that can process data, call APIs, run tasks in parallel, and execute conditional logic.
-- **Extensible Packages**: Enhance functionality with packages like `@voltagent/voice` for voice interactions.
-- **Tooling & Integrations**: Equip agents with tools to connect to external APIs, databases, and services, enabling them to perform real-world tasks. **Supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) for standardized tool interactions.**
-- **Data Retrieval & RAG**: Implement specialized retriever agents for efficient information fetching and **Retrieval-Augmented Generation (RAG)**.
-- **Memory**: Enable agents to remember past interactions for more natural and context-aware conversations.
-- **LLM Compatibility**: Works with popular AI models from OpenAI, Google, Anthropic, and more, allowing easy switching.
-- **Developer Ecosystem**: Includes helpers like `create-voltagent-app`, `@voltagent/cli`, and the visual [VoltOps LLM Observability Platform](https://console.voltagent.dev) for quick setup, monitoring, and debugging.
+Build agents with full code control and ship them with production-ready visibility and operations.
-In essence, VoltAgent helps developers build sophisticated AI applications faster and more reliably, avoiding repetitive setup and the limitations of simpler tools.
+
Core TypeScript Framework
-## Why VoltAgent?
+With the open-source framework, you can build intelligent agents with memory, tools, and multi-step workflows while connecting to any AI provider. Create sophisticated multi-agent systems where specialized agents work together under supervisor coordination.
-Building AI applications often involves a trade-off:
+- **[Core Runtime](https://voltagent.dev/docs/agents/overview/) (`@voltagent/core`)**: Define agents with typed roles, tools, memory, and model providers in one place so everything stays organized.
+- **[Workflow Engine](https://voltagent.dev/docs/workflows/overview/)**: Describe multi-step automations declaratively rather than stitching together custom control flow.
+- **[Supervisors & Sub-Agents](https://voltagent.dev/docs/agents/sub-agents/)**: Run teams of specialized agents under a supervisor runtime that routes tasks and keeps them in sync.
+- **[Tool Registry](https://voltagent.dev/docs/agents/tools/) & [MCP](https://voltagent.dev/docs/agents/mcp/)**: Ship Zod-typed tools with lifecycle hooks and cancellation, and connect to [Model Context Protocol](https://modelcontextprotocol.io/) servers without extra glue code.
+- **[LLM Compatibility](https://voltagent.dev/docs/getting-started/providers-models/)**: Swap between OpenAI, Anthropic, Google, or other providers by changing config, not rewriting agent logic.
+- **[Memory](https://voltagent.dev/docs/agents/memory/overview/)**: Attach durable memory adapters so agents remember important context across runs.
+- **[Retrieval & RAG](https://voltagent.dev/docs/rag/overview/)**: Plug in retriever agents to pull facts from your data sources and ground responses (RAG) before the model answers.
+- **[VoltAgent Knowledge Base](https://voltagent.dev/docs/rag/voltagent/)**: Use the managed RAG service for document ingestion, chunking, embeddings, and search.
+- **[Voice](https://voltagent.dev/docs/agents/voice/)**: Add text-to-speech and speech-to-text capabilities with OpenAI, ElevenLabs, or custom voice providers.
+- **[Guardrails](https://voltagent.dev/docs/guardrails/overview/)**: Intercept and validate agent input or output at runtime to enforce content policies and safety rules.
+- **[Evals](https://voltagent.dev/docs/evals/overview/)**: Run agent eval suites alongside your workflows to measure and improve agent behavior.
-1. **DIY Approach:** Using basic AI provider tools offers control but leads to complex, hard-to-manage code and repeated effort.
-2. **No-Code Builders:** Simpler initially but often restrictive, limiting customization, provider choice, and complexity.
+#### MCP Server (@voltagent/mcp-docs-server)
-VoltAgent provides a middle ground, offering structure and components without sacrificing flexibility:
+You can use the MCP server `@voltagent/mcp-docs-server` to teach your LLM how to use VoltAgent for AI-powered coding assistants like Claude, Cursor, or Windsurf. This allows AI assistants to access VoltAgent documentation, examples, and changelogs directly while you code.
-- **Build Faster:** Accelerate development with pre-built components compared to starting from scratch.
-- **Maintainable Code:** Encourages organization for easier updates and debugging.
-- **Scalability:** Start simple and easily scale to complex, multi-agent systems handling intricate workflows.
-- **Build Sophisticated Automations:** It's not just for chat. The workflow engine lets you build complex, multi-step processes for tasks like data analysis pipelines, automated content generation, or intelligent decision-making systems.
-- **Flexibility:** Full control over agent behavior, LLM choice, tool integrations, and UI connections.
-- **Avoid Lock-in:** Freedom to switch AI providers and models as needed.
-- **Cost Efficiency:** Features designed to optimize AI service usage and reduce redundant calls.
-- **Visual Monitoring:** Use the [VoltOps LLM Observability Platform](https://console.voltagent.dev) to track agent performance, inspect state, and debug visually.
-
-VoltAgent empowers developers to build their envisioned AI applications efficiently, from simple helpers to complex systems.
+📖 [How to setup MCP docs server](https://voltagent.dev/docs/getting-started/mcp-docs-server/)
## ⚡ Quick Start
@@ -162,13 +139,88 @@ Your agent is now running! To interact with it:
4. Start Chatting: On the agent detail page, click the chat icon in the bottom right corner to open the chat window.
5. Send a Message: Type a message like "Hello" and press Enter.
-[](https://console.voltagent.dev/)
+[](https://github.com/user-attachments/assets/26340c6a-be34-48a5-9006-e822bf6098a7)
### Running Your First Workflow
-Your new project also includes a powerful workflow engine. You can test the pre-built `expenseApprovalWorkflow` directly from the VoltOps console:
+Your new project also includes a powerful workflow engine.
+
+The expense approval workflow demonstrates human-in-the-loop automation with suspend/resume capabilities:
+
+```typescript
+import { createWorkflowChain } from "@voltagent/core";
+import { z } from "zod";
+
+export const expenseApprovalWorkflow = createWorkflowChain({
+ id: "expense-approval",
+ name: "Expense Approval Workflow",
+ purpose: "Process expense reports with manager approval for high amounts",
+
+ input: z.object({
+ employeeId: z.string(),
+ amount: z.number(),
+ category: z.string(),
+ description: z.string(),
+ }),
+ result: z.object({
+ status: z.enum(["approved", "rejected"]),
+ approvedBy: z.string(),
+ finalAmount: z.number(),
+ }),
+})
+ // Step 1: Validate expense and check if approval needed
+ .andThen({
+ id: "check-approval-needed",
+ resumeSchema: z.object({
+ approved: z.boolean(),
+ managerId: z.string(),
+ comments: z.string().optional(),
+ adjustedAmount: z.number().optional(),
+ }),
+ execute: async ({ data, suspend, resumeData }) => {
+ // If we're resuming with manager's decision
+ if (resumeData) {
+ return {
+ ...data,
+ approved: resumeData.approved,
+ approvedBy: resumeData.managerId,
+ finalAmount: resumeData.adjustedAmount || data.amount,
+ };
+ }
+
+ // Check if manager approval is needed (expenses over $500)
+ if (data.amount > 500) {
+ await suspend("Manager approval required", {
+ employeeId: data.employeeId,
+ requestedAmount: data.amount,
+ });
+ }
+
+ // Auto-approve small expenses
+ return {
+ ...data,
+ approved: true,
+ approvedBy: "system",
+ finalAmount: data.amount,
+ };
+ },
+ })
+ // Step 2: Process the final decision
+ .andThen({
+ id: "process-decision",
+ execute: async ({ data }) => {
+ return {
+ status: data.approved ? "approved" : "rejected",
+ approvedBy: data.approvedBy,
+ finalAmount: data.finalAmount,
+ };
+ },
+ });
+```
-
+You can test the pre-built `expenseApprovalWorkflow` directly from the VoltOps console:
+
+[](https://github.com/user-attachments/assets/3d3ea67b-4ab5-4dc0-932d-cedd92894b18)
1. **Go to the Workflows Page:** After starting your server, go directly to the [Workflows page](https://console.voltagent.dev/workflows).
2. **Select Your Project:** Use the project selector to choose your project (e.g., "my-agent-app").
@@ -184,39 +236,106 @@ Your new project also includes a powerful workflow engine. You can test the pre-
```
5. **View the Results:** After execution, you can inspect the detailed logs for each step and see the final output directly in the console.
-## Key Features
-
-- **Agent Core:** Define agents with descriptions, LLM providers, tools, and memory management.
-- **Workflow Engine:** Orchestrate complex, multi-step automations with a powerful and declarative API (`andThen`, `andAgent`, `andAll`, `andRace`, `andWhen`).
-- **Multi-Agent Systems:** Build complex workflows using Supervisor Agents coordinating multiple specialized Sub-Agents.
-- **Tool Usage & Lifecycle:** Equip agents with custom or pre-built tools (functions) with type-safety (Zod), lifecycle hooks, and cancellation support to interact with external systems.
-- **Flexible LLM Support:** Integrate seamlessly with various LLM providers (OpenAI, Anthropic, Google, etc.) and easily switch between models.
-- **Memory Management:** Enable agents to retain context across interactions using different configurable memory providers.
-- **Observability & Debugging:** Visually monitor agent states, interactions, logs, and performance via the [VoltOps LLM Observability Platform](https://console.voltagent.dev).
-- **Custom API Endpoints:** Extend the VoltAgent API server with your own custom endpoints to build specialized functionality on top of the core framework.
-- **Voice Interaction:** Build voice-enabled agents capable of speech recognition and synthesis using the `@voltagent/voice` package.
-- **Data Retrieval & RAG:** Integrate specialized retriever agents for efficient information fetching and **Retrieval-Augmented Generation (RAG)** from various sources.
-- **Model Context Protocol (MCP) Support:** Connect to external tool servers (HTTP/stdio) adhering to the [MCP standard](https://modelcontextprotocol.io/) for extended capabilities.
-- **Prompt Engineering Tools:** Leverage utilities like `createPrompt` for crafting and managing effective prompts for your agents.
-- **Framework Compatibility:** Designed for easy integration into existing Node.js applications and popular frameworks.
-
-## Use Cases
-
-VoltAgent is versatile and can power a wide range of AI-driven applications:
-
-- **Complex Workflow Automation:** Orchestrate multi-step processes involving various tools, APIs, and decision points using coordinated agents.
-- **Intelligent Data Pipelines:** Build agents that fetch, process, analyze, and transform data from diverse sources.
-- **AI-Powered Internal Tools & Dashboards:** Create interactive internal applications that leverage AI for analysis, reporting, or task automation, often integrated with UIs using hooks.
-- **Automated Customer Support Agents:** Develop sophisticated chatbots that can understand context (memory), use tools (e.g., check order status), and escalate complex issues.
-- **Repository Analysis & Codebase Automation:** Analyze code repositories, automate refactoring tasks, generate documentation, or manage CI/CD processes.
-- **Retrieval-Augmented Generation (RAG) Systems:** Build agents that retrieve relevant information from knowledge bases (using retriever agents) before generating informed responses.
-- **Voice-Controlled Interfaces & Applications:** Utilize the `@voltagent/voice` package to create applications that respond to and generate spoken language.
-- **Personalized User Experiences:** Develop agents that adapt responses and actions based on user history and preferences stored in memory.
-- **Real-time Monitoring & Alerting:** Design agents that continuously monitor data streams or systems and trigger actions or notifications based on defined conditions.
-- **And Virtually Anything Else...**: If you can imagine an AI agent doing it, VoltAgent can likely help you build it! ⚡
+## Examples
+
+For more examples, visit our [examples repository](https://github.com/VoltAgent/voltagent/tree/main/examples).
+
+- **[Airtable Agent](https://voltagent.dev/examples/guides/airtable-agent)** - React to new records and write updates back into Airtable with VoltOps actions.
+- **[Slack Agent](https://voltagent.dev/examples/guides/slack-agent)** - Respond to channel messages and reply via VoltOps Slack actions.
+- **[ChatGPT App With VoltAgent](https://voltagent.dev/examples/agents/chatgpt-app)** - Deploy VoltAgent over MCP and connect to ChatGPT Apps.
+- **[WhatsApp Order Agent](https://voltagent.dev/examples/agents/whatsapp-ai-agent)** - Build a WhatsApp chatbot that handles food orders through natural conversation. ([Source](https://github.com/VoltAgent/voltagent/tree/main/examples/with-whatsapp))
+- **[YouTube to Blog Agent](https://voltagent.dev/examples/agents/youtube-blog-agent)** - Convert YouTube videos into Markdown blog posts using a supervisor agent with MCP tools. ([Source](https://github.com/VoltAgent/voltagent/tree/main/examples/with-youtube-to-blog))
+- **[AI Ads Generator Agent](https://voltagent.dev/examples/agents/ai-instagram-ad-agent)** - Generate Instagram ads using BrowserBase Stagehand and Google Gemini AI. ([Source](https://github.com/VoltAgent/voltagent/tree/main/examples/with-ad-creator))
+- **[AI Recipe Generator Agent](https://voltagent.dev/examples/agents/recipe-generator)** - Create personalized cooking suggestions based on ingredients and preferences. ([Source](https://github.com/VoltAgent/voltagent/tree/main/examples/with-recipe-generator) | [Video](https://youtu.be/KjV1c6AhlfY))
+- **[AI Research Assistant Agent](https://voltagent.dev/examples/agents/research-assistant)** - Multi-agent research workflow for generating comprehensive reports. ([Source](https://github.com/VoltAgent/voltagent/tree/main/examples/with-research-assistant) | [Video](https://youtu.be/j6KAUaoZMy4))
+
+
VoltOps Console: LLM Observability - Automation - Deployment
+
+VoltOps Console is the platform side of VoltAgent, providing observability, automation, and deployment so you can monitor and debug agents in production with real-time execution traces, performance metrics, and visual dashboards.
+
+🎬 [Try Live Demo](https://console.voltagent.dev/demo)
+
+📖 [VoltOps Documentation](https://voltagent.dev/voltops-llm-observability-docs/)
+
+🚀 [VoltOps Platform](https://voltagent.dev/voltops-llm-observability/)
+
+### Observability & Tracing
+
+Deep dive into agent execution flow with detailed traces and performance metrics.
+
+
+
+### Dashboard
+
+Get a comprehensive overview of all your agents, workflows, and system performance metrics.
+
+
+
+### Logs
+
+Track detailed execution logs for every agent interaction and workflow step.
+
+
+
+### Memory Management
+
+Inspect and manage agent memory, context, and conversation history.
+
+
+
+### Traces
+
+Analyze complete execution traces to understand agent behavior and optimize performance.
+
+
+
+### Prompt Builder
+
+Design, test, and refine prompts directly in the console.
+
+
+
+### Deployment
+
+Deploy your agents to production with one-click GitHub integration and managed infrastructure.
+
+
+
+📖 [VoltOps Deploy Documentation](https://voltagent.dev/docs/deployment/voltops/)
+
+### Triggers & Actions
+
+Automate agent workflows with webhooks, schedules, and custom triggers to react to external events.
+
+
+
+### Monitoring
+
+Monitor agent health, performance metrics, and resource usage across your entire system.
+
+
+
+### Guardrails
+
+Set up safety boundaries and content filters to ensure agents operate within defined parameters.
+
+
+
+### Evals
+
+Run evaluation suites to test agent behavior, accuracy, and performance against benchmarks.
+
+
+
+### RAG (Knowledge Base)
+
+Connect your agents to knowledge sources with built-in retrieval-augmented generation capabilities.
+
+
## Learning VoltAgent
+- **[Start with interactive tutorial](https://voltagent.dev/tutorial/introduction/)** to learn the fundamentals building AI Agents.
- **[Documentation](https://voltagent.dev/docs/)**: Dive into guides, concepts, and tutorials.
- **[Examples](https://github.com/voltagent/voltagent/tree/main/examples)**: Explore practical implementations.
- **[Blog](https://voltagent.dev/blog/)**: Read more about technical insights, and best practices.
@@ -231,10 +350,8 @@ Big thanks to everyone who's been part of the VoltAgent journey, whether you've
VoltAgent is a community effort, and it keeps getting better because of people like you.
-
-
-Your stars help us reach more developers! If you find VoltAgent useful, please consider giving us a star on GitHub to support the project and help others discover it.
+
## License
-Licensed under the MIT License, Copyright © 2025-present VoltAgent.
+Licensed under the MIT License, Copyright © 2026-present VoltAgent.
diff --git a/website/docs/agents/plan-agent.md b/website/docs/agents/plan-agent.md
index 584fe1255..0a32a79f7 100644
--- a/website/docs/agents/plan-agent.md
+++ b/website/docs/agents/plan-agent.md
@@ -61,7 +61,7 @@ const agent = new PlanAgent({
tools: [internetSearch],
});
-const result = await agent.generateText("What is LangGraph?");
+const result = await agent.generateText("What is VoltAgent?");
console.log(result.text);
```