All LangChain JavaScript integration providers

Integrate with Anthropic's Claude models for advanced reasoning and conversation.

Access AWS services and foundation models through comprehensive integrations.

Integrate with Google's AI services including Gemini and Gemini Enterprise Agent Platform.

Connect to Microsoft Azure services and AI platforms.

Build with GPT models and OpenAI's comprehensive AI platform.

Open event-based protocol for connecting LangGraph agents to any frontend.

React stack and Python middleware for Deep Agents, LangGraph agents, FastAPI, and generative UI.

Render adaptive, agent-generated interfaces from LangGraph and Deep Agents using OpenUI.

Observability and customer analytics for production AI agents.

Classify state into typed decisions and calibrated probabilities with Jev.

Claude models for advanced conversational AI and reasoning.

OpenAI models through Microsoft Azure's enterprise platform.

Baidu's Qianfan platform for Chinese language AI models.

Unified Bedrock Converse API for multiple foundation models.

Ultra-fast inference with Cerebras Systems' AI processors.

Marketplace of real residential Chrome sessions for AI agents.

Run WebLLM models locally with WebGPU through LangChain, LangGraph, and Deep Agents.

Run AI models on Cloudflare's edge computing platform.

Cohere's language models for text generation and understanding.

DeepSeek's advanced reasoning and coding models.

Specialized AI model hosting for open, proprietary, and custom stacks, plus GPU Cloud and hosted AI agents.

Mock chat model for testing and development purposes.

Unified AI gateway for 22+ models with OpenAI-compatible API.

Google's Gemini models via AI Studio and Gemini Enterprise Agent Platform.

Ultra-fast inference with Groq's specialized hardware.

Multimodal chat model with structured output over an OpenAI-compatible API.

Mistral's efficient and powerful language models.

Run local models with Ollama's lightweight inference engine.

Access models from multiple providers through OpenRouter's unified API.

GPT models and OpenAI's comprehensive chat capabilities.

Tools for agents to search Recall memory, ask it a question about the user, and save a fact.

Open-weight chat and multimodal models with image and video input over SCX's OpenAI-compatible API.

Governed OpenAI-compatible endpoint for model access, policy checks, and usage accounting.

xAI's Grok models for conversational AI.

Yandex's AI models and language processing services.

OpenAI models through Microsoft Azure's enterprise platform.

AI models on Cloudflare's edge computing platform.

Cohere's language models for various NLP tasks.

Google Cloud's enterprise AI and ML platform.

JigsawStack's AI infrastructure and model services.

Mistral's open-source and commercial language models.

Local model serving with Ollama's simple interface.

GPT models and OpenAI's language model APIs.

Yandex's language models and AI services.

OpenAI embeddings through Microsoft Azure platform.

Baidu's text embedding models for Chinese content.

Foundation model embeddings through Amazon Bedrock.

Text embeddings on Cloudflare's edge AI platform.

Cohere's multilingual embedding models.

Specialized AI model hosting for open, proprietary, and custom stacks, plus GPU Cloud and hosted AI agents.

Google's embedding models for text representation.

Enterprise embedding models through Gemini Enterprise Agent Platform.

Minimax's text embedding and representation models.

Mistral's efficient embedding models.

High-quality multilingual embedding models.

Nomic's open-source embedding models.

Local embedding models through Ollama.

OpenAI's text-embedding models for semantic search.

Oracle's embedding models for AI applications.

Pinecone's embedding models and vector database.

SAP HANA Cloud's built-in embedding models for in-database vector generation.

4096-dimension E5-Mistral embeddings over SCX's OpenAI-compatible API.

Vector search in Azure DocumentDB (formerly Azure Cosmos DB for MongoDB vCore).

Vector storage in Azure Cosmos DB NoSQL API.

Serverless vector database on Cloudflare's edge.

PostgreSQL with vector extensions on Google Cloud.

Vector, BM25, and hybrid retrieval over one engine on object storage.

Serverless database for RAG and agents.

In-memory vector storage for development and testing.

Vector search in MongoDB Atlas cloud database.

Oracle Vector Search for hybrid retrieval and storage.

Managed vector database for machine learning applications.

Open-source vector similarity search engine.

In-memory database with vector search capabilities.

Vector store fully integrated into the SAP HANA Cloud database.

Open-source vector database with GraphQL API.

Load and parse JSON files with flexible structure handling.

Load newline-delimited JSON files.

Load multiple files of different types simultaneously.

Load Oracle AI Vector Search tables and compatible files.

Load plain text files with encoding detection.

Load data from Google Cloud SQL PostgreSQL databases.

Load runs and datasets from LangSmith.

Cloud sandboxes for AI agents with fast cold starts.

High-accuracy multilingual speech-to-text API.

Retrieve from published Sourcey docs sites using build artefacts Sourcey already emits.

Load transcripts and metadata from YouTube, TikTok, and more.

Generate metadata tags for documents using OpenAI.

Rerank documents using Cohere's reranking models.

Rerank and compress documents using MixedBread AI.

Web search tool for LangChain.js agents, free by default with no key. Pay-per-call Extract and Render ($0.005, x402) for full pages and JS-rendered sites.

Pay-per-call web, data, crypto, memory, and inbox tools for agents, paid with a credit token or USDC via x402.

Paid data tools from aiworker's OpenAPI catalogue; each call settles itself in USDC over x402 from the agent's wallet, with no API key.

Email toolkit that provisions an agent-owned inbox by proof of work and sends and receives over JMAP.

Secure code execution in Azure Dynamic Sessions.

LangChain tools with application-defined permissions, stable operation identities and status-only recovery for cooperating services.

Exposes 200+ service integrations (Slack, GitHub, Gmail, Linear, Stripe, and more) to LangChain agents as tools with OAuth.

Generate images using OpenAI's DALL-E models.

Dataset marketplace tools for public search, sample previews, and bounty discovery, with account-authenticated data retrieval.

Code execution and analysis with Decodo.

AI-powered search engine for better results.

Fizzl checks transactions, signatures, tokens, wallet approvals, and x402 paid endpoints before AI agents sign or pay.

GetYouTubeTranscript is an API for YouTube video transcripts (optionally with per-line timestamps) and YouTube search

Toolkit for Instant Expert's MCP server that sends paid invitations to specific experts for a short call or written answer, with a free test mode.

AI infrastructure tools from JigsawStack.

Parse and manipulate JSON data structures.

Execute code in AWS Lambda functions.

AI text-to-video, image-to-video, and image generation tools behind one API key.

Tools that pause an agent until a human approves on their phone; alerts ring through silent mode and escalate to a voice call.

Model Context Protocol tools and utilities.

MCP tools from SilberArrows for Mercedes-Benz Service A/B reminders, service explanations, and warning-light guidance.

Generate tools from OpenAPI specifications.

Summarize, chunk, and serve data with Oracle AI Vector Search tools.

Query databases using natural language.

Web search results from the Perplexity Search API.

Semantic search over free stock photos from Unsplash, Pexels, Pixabay, and more, returning each photo with license and credit.

People search and contact enrichment (work emails, phone numbers, profiles, and firmographics) across multiple data providers

Checks whether a cold or marketing email to an address is legal in eight countries, and returns the deciding rule, footer requirements and a signed receipt.

Phone approvals for LangGraph.js agents: ask on the user's phone and route only on Approve; no answer means no action.

Multi-engine web search API for AI applications and data aggregation.

Add wallet-signed messaging tools to LangChain agents.

Keyless tools over Sato Hub's index of onchain-agent building blocks: search listings, Preflight lookups, swap venues, and build plans.

Tools for x402 payments that verify merchant, price, and terms before payment via LangChain MCP adapters.

Unified SERP API across 33 search engines with geo-targeting.

Web crawling capabilities with Tavily.

Extract structured data from web pages.

Map and visualize web crawling results.

AI-optimized search for retrieval applications.

Comprehensive research on a given topic with Tavily.

Retrieve status and results of a research task using its request ID.

Web page extraction API returning clean Markdown plus fixed-schema JSON for article metadata, product prices and tables.

Real-time web search and content extraction for LLMs.

Query vector databases as tools.

Retrieve from Amazon Bedrock Knowledge Bases.

AI-powered web search and retrieval.

Retriever, document loader and agent tool for FoxNose collections, with text, vector, hybrid and vector-boosted search over the Flux delivery API.

Hypothetical Document Embeddings for better retrieval.

Enterprise search with Amazon Kendra.

Retriever returning Documents from the Perplexity Search API.

Retrieves the facts Recall learned about a user, and the user's matching messages, as documents.

Self-querying retriever over SAP HANA Cloud Vector Engine.

Time-aware document retrieval and ranking.

LangGraph BaseStore on local SQLite: puts record the writer, version instead of overwrite, and keep belief history.

Local file system storage for development.

Fast in-memory storage for temporary data.

Cache LLM responses in Azure Cosmos DB.

Multi-tier cache for AI agents backed by Valkey or Redis.

Supervises an agent's tool calls with BRYDGE and checks the destination system's own records to report whether each action happened as permitted.

Chat message history stored in a Recall session, so Recall also learns about the user from it.

Long-term memory for create_agent agents: adds what Recall learned about the user to the system prompt and records each exchange.

OpenTelemetry instrumentation that records LangChain and LangGraph operations using OpenInference semantic conventions.

Trace LangChain.js, LangGraph.js, and Langflow-style callback runs in Respan.

Validate prompts for prompt injection before they reach your model.