Top providers
Anthropic
Integrate with Anthropic’s Claude models for advanced reasoning and conversation.
AWS
Access AWS services and foundation models through comprehensive integrations.
Integrate with Google’s AI services including Gemini and Vertex AI.
Microsoft
Connect to Microsoft Azure services and AI platforms.
OpenAI
Build with GPT models and OpenAI’s comprehensive AI platform.
LangGraph integrations
Connect LangGraph agents to front ends and observability platforms.AG-UI Protocol
Open event-based protocol for connecting LangGraph agents to any frontend.
CopilotKit
React stack and Python middleware for Deep Agents, LangGraph agents, FastAPI, and generative UI.
OpenUI
Render adaptive, agent-generated interfaces from LangGraph and Deep Agents using OpenUI.
The Context Company
Observability and customer analytics for production AI agents.
Chat models
Anthropic
Claude models for advanced conversational AI and reasoning.
Azure OpenAI
OpenAI models through Microsoft Azure’s enterprise platform.
Baidu Qianfan
Baidu’s Qianfan platform for Chinese language AI models.
Bedrock Converse
Unified Bedrock Converse API for multiple foundation models.
Cerebras
Ultra-fast inference with Cerebras Systems’ AI processors.
Ceki
Marketplace of real residential Chrome sessions for AI agents.
Cloudflare Workers AI
Run AI models on Cloudflare’s edge computing platform.
Cohere
Cohere’s language models for text generation and understanding.
DeepSeek
DeepSeek’s advanced reasoning and coding models.
Fake LLM
Mock chat model for testing and development purposes.
FuturMix
Unified AI gateway for 22+ models with OpenAI-compatible API.
Google Gemini
Google’s Gemini models via AI Studio and Vertex AI.
Groq
Ultra-fast inference with Groq’s specialized hardware.
Interfaze
Multimodal chat model with structured output over an OpenAI-compatible API.
Mistral
Mistral’s efficient and powerful language models.
Ollama
Run local models with Ollama’s lightweight inference engine.
OpenRouter
Access models from multiple providers through OpenRouter’s unified API.
OpenAI
GPT models and OpenAI’s comprehensive chat capabilities.
SCX
Open-weight chat and multimodal models with image and video input over SCX’s OpenAI-compatible API.
xAI
xAI’s Grok models for conversational AI.
Yandex
Yandex’s AI models and language processing services.
LLMs
Azure OpenAI
OpenAI models through Microsoft Azure’s enterprise platform.
Cloudflare Workers AI
AI models on Cloudflare’s edge computing platform.
Cohere
Cohere’s language models for various NLP tasks.
Google Vertex AI
Google Cloud’s enterprise AI and ML platform.
JigsawStack
JigsawStack’s AI infrastructure and model services.
Mistral
Mistral’s open-source and commercial language models.
Ollama
Local model serving with Ollama’s simple interface.
OpenAI
GPT models and OpenAI’s language model APIs.
Yandex
Yandex’s language models and AI services.
Text embedding models
Azure OpenAI
OpenAI embeddings through Microsoft Azure platform.
Baidu Qianfan
Baidu’s text embedding models for Chinese content.
Amazon Bedrock
Foundation model embeddings through Amazon Bedrock.
Cloudflare AI
Text embeddings on Cloudflare’s edge AI platform.
Cohere
Cohere’s multilingual embedding models.
Google Generative AI
Google’s embedding models for text representation.
Google Vertex AI
Enterprise embedding models through Vertex AI.
Minimax
Minimax’s text embedding and representation models.
Mistral
Mistral’s efficient embedding models.
MixedBread AI
High-quality multilingual embedding models.
Nomic
Nomic’s open-source embedding models.
Ollama
Local embedding models through Ollama.
OpenAI
OpenAI’s text-embedding models for semantic search.
Oracle AI Database
Oracle’s embedding models for AI applications.
Pinecone
Pinecone’s embedding models and vector database.
SAP HANA Internal Embeddings
SAP HANA Cloud’s built-in embedding models for in-database vector generation.
SCX
4096-dimension E5-Mistral embeddings over SCX’s OpenAI-compatible API.
Vector stores
Azure DocumentDB
Vector search in Azure DocumentDB (formerly Azure Cosmos DB for MongoDB vCore).
Azure Cosmos DB NoSQL
Vector storage in Azure Cosmos DB NoSQL API.
Cloudflare Vectorize
Serverless vector database on Cloudflare’s edge.
Google Cloud SQL PostgreSQL
PostgreSQL with vector extensions on Google Cloud.
Infino
Vector, BM25, and hybrid retrieval over one engine on object storage.
LambdaDB
Serverless database for RAG and agents.
Memory Vector Store
In-memory vector storage for development and testing.
MongoDB Atlas
Vector search in MongoDB Atlas cloud database.
Oracle AI Database
Oracle Vector Search for hybrid retrieval and storage.
Pinecone
Managed vector database for machine learning applications.
Qdrant
Open-source vector similarity search engine.
Redis
In-memory database with vector search capabilities.
SAP HANA Cloud Vector Engine
Vector store fully integrated into the SAP HANA Cloud database.
Weaviate
Open-source vector database with GraphQL API.
Document loaders
File loaders
JSON
Load and parse JSON files with flexible structure handling.
JSON Lines
Load newline-delimited JSON files.
Multi-File
Load multiple files of different types simultaneously.
Oracle AI Database
Load Oracle AI Vector Search tables and compatible files.
Text
Load plain text files with encoding detection.
Web loaders
Google Cloud SQL PostgreSQL
Load data from Google Cloud SQL PostgreSQL databases.
LangSmith
Load runs and datasets from LangSmith.
Leap0
Cloud sandboxes for AI agents with fast cold starts.
Soniox
High-accuracy multilingual speech-to-text API.
Sourcey
Retrieve from published Sourcey docs sites using build artefacts Sourcey already emits.
Supadata
Load transcripts and metadata from YouTube, TikTok, and more.
Document transformers
OpenAI Metadata Tagger
Generate metadata tags for documents using OpenAI.
Document compressors
Cohere Rerank
Rerank documents using Cohere’s reranking models.
MixedBread AI
Rerank and compress documents using MixedBread AI.
Tools
Azure Dynamic Sessions
Secure code execution in Azure Dynamic Sessions.
DALL-E
Generate images using OpenAI’s DALL-E models.
Decodo
Code execution and analysis with Decodo.
Exa Search
AI-powered search engine for better results.
JigsawStack
AI infrastructure tools from JigsawStack.
JSON Tool
Parse and manipulate JSON data structures.
Lambda Agent
Execute code in AWS Lambda functions.
MCP Toolbox
Model Context Protocol tools and utilities.
OpenAPI
Generate tools from OpenAPI specifications.
Oracle AI Database
Summarize, chunk, and serve data with Oracle AI Vector Search tools.
SQL
Query databases using natural language.
Perplexity Search
Web search results from the Perplexity Search API.
Serpex
Multi-engine web search API for AI applications and data aggregation.
TalorData
Unified SERP API across 33 search engines with geo-targeting.
Tavily Crawl
Web crawling capabilities with Tavily.
Tavily Extract
Extract structured data from web pages.
Tavily Map
Map and visualize web crawling results.
Tavily Search
AI-optimized search for retrieval applications.
Tavily Research
Comprehensive research on a given topic with Tavily.
Tavily GET Research
Retrieve status and results of a research task using its request ID.
You.com
Real-time web search and content extraction for LLMs.
Vector Store
Query vector databases as tools.
Retrievers
Bedrock Knowledge Bases
Retrieve from Amazon Bedrock Knowledge Bases.
Exa
AI-powered web search and retrieval.
HyDE
Hypothetical Document Embeddings for better retrieval.
Kendra
Enterprise search with Amazon Kendra.
Perplexity Search
Retriever returning Documents from the Perplexity Search API.
SAP HANA Self Query
Self-querying retriever over SAP HANA Cloud Vector Engine.
Time-Weighted
Time-aware document retrieval and ranking.
Stores
File System
Local file system storage for development.
In-Memory
Fast in-memory storage for temporary data.
LLM caching
Azure Cosmos DB NoSQL
Cache LLM responses in Azure Cosmos DB.
BetterDB Agent Cache
Multi-tier cache for AI agents backed by Valkey or Redis.
Callbacks
Respan
Trace LangChain.js, LangGraph.js, and Langflow-style callback runs in Respan.
SafePrompt
Validate prompts for prompt injection before they reach your model.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.