Integrate NVIDIA LLM into your AI workflows

Delegate tasks to remote agents over the A2A (Agent2Agent) protocol.

With the AI Agent, you can chat with the AI agent.

AI Agent Utils brings Claude Code-inspired tools and agent skills.

AI Helper component for image analysis and generation.

AI Helper component for text analysis and generation.

Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies.

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Stores session-based conversation history as JSON objects in an Amazon S3 bucket.

Azure OpenAI is a research organization that aims to develop and direct artificial intelligence (AI) in ways that benefit humanity as a whole.

Bolna AI is an open-source platform that enables businesses to create and deploy voice-driven conversational agents

AI-powered browser automation that enables agents to perform web tasks such as navigating websites and extracting data.

Cassandra Chat Memory stores conversation history in Apache Cassandra for distributed, scalable persistent storage.

Built-in session-based chat memory.

Runs configured guardrail checks on the user prompt.

Couchbase is a distributed, JSON document database, with all the desired capabilities of a relational DBMS.

User-defined LLM-based guardrail.

User-defined regex guardrail — flags or masks matches of a custom pattern.

DeepSeek AI provides the open-source DeepSeek V3 model, renowned for its cutting-edge reasoning and problem-solving capabilities.

Document Enricher.

Document Joiner.

Document Reader.

Document Splitter.

ElevenLabs is an AI-powered voice synthesis company specializing in ultra-realistic text-to-speech and voice cloning technology.

Firecrawl allows you to turn entire websites into LLM-ready markdown

Google Gemini is a multimodal generative AI model. This component supports both Vertex AI and the Gemini Developer API.

Google BigQuery is the autonomous data to AI platform, automating the entire data life cycle, from ingestion to AI-driven insights, so you can go from data to AI to action faster.

The LPU Inference Engine by Groq is a hardware and software platform that delivers exceptional compute speed, quality, and energy efficiency.

HeyGen is an AI Video Generator that lets you create explainer videos, marketing and sales promos, product demos, training and onboarding content.

In Memory session-based Chat Memory.

LLM-based detection of jailbreak / prompt-injection attempts.

JDBC Chat Memory stores session-based conversation history in a relational database.

Flags or masks the input if any listed keyword appears in it.

Search ByteChef's internal knowledge base to retrieve relevant document chunks using semantic similarity search powered by vector embeddings.

LiteLLM is a self-hosted AI gateway proxy that provides a unified OpenAI-compatible API for 100+ LLM providers, enabling model fallbacks, load balancing, and spend tracking through a single endpoint.

LLM-assisted detection and masking of PII (names, addresses, emails, etc.).

MariaDB Vector Store uses MariaDB 11.7+ native vector storage and similarity search capabilities to store and query document embeddings.

Milvus is an open-source vector database that has garnered significant attention in the fields of data science and machine learning.

Open, efficient, helpful and trustworthy AI models through ground-breaking innovations.

A modular RAG (Retrieval-Augmented Generation) component that provides a flexible and customizable approach to building RAG systems. It allows you to combine different retrieval, augmentation, and generation strategies into a cohesive pipeline for enhanced AI-driven information processing and response generation.

MongoDB Chat Memory stores conversation history in MongoDB for flexible, document-based persistent storage.

MongoDB Atlas Vector Search combines document storage with vector similarity search, enabling storage and retrieval of high-dimensional embeddings for AI and machine learning applications.

The NanoGPT API allows you to generate text, images and video using any AI model available.

Neo4j is an open-source NoSQL graph database. It is a fully transactional database (ACID) that stores data structured as graphs consisting of nodes, connected by relationships.

Neo4j Chat Memory stores conversation history in Neo4j graph database for persistent storage with graph-based relationships.

LLM-based detection of NSFW content.

Get up and running with large language models.

OpenAI is a research organization that aims to develop and direct artificial intelligence (AI) in ways that benefit humanity as a whole.

OpenRouter provides a unified API that gives you access to hundreds of AI models through a single endpoint, while automatically handling fallbacks and selecting the most cost-effective options.

Oracle Vector Store uses Oracle Database 23ai's native vector storage and similarity search capabilities to store and query document embeddings.

Perplexity AI provides a unique AI service that integrates its language models with real-time search capabilities.

PGVector is an open-source PostgreSQL extension for vector similarity search.

Detects — and optionally masks — personally identifiable information.

Pinecone is a vector database designed for efficient similarity search and storage of high-dimensional data, commonly used in machine learning and AI applications.

Qdrant is an open-source vector similarity search engine designed to handle high-dimensional data, enabling efficient and scalable nearest neighbor search for applications like recommendation systems and machine learning.

Query Augmenter.

Query Expander.

Query Transformer.

A component that enables Question-Answer Retrieval Augmented Generation (RAG) capabilities. It combines natural language processing with document retrieval to provide accurate answers based on the given context.

Redis Chat Memory stores session-based conversation history in Redis.

Redis is an open-source, in-memory data structure store used as a database, cache, and message broker, known for its high performance and support for various data structures like strings, hashes, lists, sets, and more.

Amazon S3 Vector Store uses AWS S3 as a persistent storage backend for vector embeddings, enabling scalable and durable similarity search.

Runs configured sanitizers on the model response.

ScrapeGraphAI is a web scraping python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents.

Detects — and optionally masks — API keys and credential-shaped secrets.

Activating humanity's potential through generative AI. Open models in every modality, for everyone, everywhere.

Tavily is an AI-powered search tool designed to help users quickly find accurate, relevant and up-to-date information from the web.

LLM-based check that input stays within an allowed topic.

Typesense is an open-source, in-memory search engine designed for fast, typo-tolerant, and relevance-focused full-text search across large datasets.

Detects — and optionally masks — URLs outside a configured allowlist.

Vector Store Chat Memory.

Vector Store Document Retriever.

Weaviate is an open-source vector search engine and database that enables efficient storage, retrieval, and management of high-dimensional data, often used in machine learning and AI applications.