Skip to main content

Integrations

Connect Cerebras Inference to the agent frameworks, dev tools, and platforms you already use

Agentic Frameworks

AG2

Open-source framework for building and orchestrating multi-agent AI workflows.

Agno

Lightweight framework for building multi-modal AI agents.

Browser-Use

Enable AI agents to control web browsers for automated navigation and data extraction.

CrewAI

Open-source platform designed to orchestrate workflows of complex AI agents.

Stagehand

Open-source AI-powered framework for reliable browser automation.

AI Development Kits

Vercel AI SDK

Open-source toolkit by Vercel for building AI applications using JavaScript and TypeScript.

AI Suite

Unified interface for accessing multiple LLM providers with easy comparison and switching.

Milvus

Open-source vector database for building high-performance RAG applications.

Coding Tools

Aider

AI pair programming tool for editing code in your terminal with natural language commands.

Cline

Open-source AI coding assistant to bring fast Cerebras Inference into your dev flow.

OpenCode

Open-source AI coding agent built for the terminal that integrates deeply with developer tools for coding automation.

VS Code

Free and extensible source code editor that supports multiple languages and offers features like Git integration, and a vast marketplace of extensions.

KiloCode

AI-powered autonomous coding assistant for VS Code.

Containerization

Docker

Platform for containerizing applications and environments.

Observability & Evaluation

Arize Phoenix

Open-source AI observability platform for tracing, evaluation, and debugging LLM applications.

Braintrust

LLMOps platform for evaluation, observability, and monitoring of AI applications.

Helicone

Open-source LLM observability platform for monitoring, debugging, and optimizing AI applications with detailed analytics.

Langfuse

Open-source LLM engineering platform for debugging, tracing, and evaluating AI applications.

Opik

Open-source platform for evaluating, testing, and monitoring LLM applications.

Weave

Lightweight toolkit by Weights & Biases for tracking and evaluating LLM applications.

Cloudflare AI Gateway

Route, cache, and monitor AI API requests with analytics and rate limiting.

Kong API Gateway

Cloud-native API gateway with AI Proxy plugin for secure traffic management, monitoring, and routing of Cerebras inference requests.

Operant

Real-time AI security gateway with inline threat detection, PII redaction, and rate limiting for Cerebras Inference traffic.

LLM Integration Tools

Exa

Web search and content extraction APIs for grounding AI agents with current web data.

Hugging Face

Unified Inference Providers API for accessing multiple LLM providers with support for Python, JavaScript, and streaming.

Llama Index

Tool for connecting LLMs to external data sources.

Maxim

Enterprise-grade platform for simulating, evaluating, and observing AI agents with real-time monitoring and testing.

Parallel

Web research APIs for AI agents with search, extraction, and real-time monitoring capabilities.

LLM Application Frameworks

Instructor

Library for type-safe, validated structured outputs from LLMs using Pydantic models.

LangChain

Framework for developing applications powered by large language models.

LangGraph

Framework for building stateful, multi-actor AI agents with LangChain.

Pydantic AI

Python framework for building production-grade AI agents with type-safe structured outputs and validation.

Llama Stack

Framework for building generative AI applications.

Document Processing

Reducto

Document parsing platform for extracting structured data from PDFs, images, and documents.

Unstructured

Advanced document processing platform for extracting structured data from PDFs, images, and complex documents with AI-powered parsing.

Real-Time Audio

Cartesia

Voice AI platform that builds ultra-realistic, real-time speech generation and voice agent development tools.

LiveKit

Open-source platform for real-time audio and video AI.

ElevenLabs

Voice AI platform for ultra-fast text-to-speech generation and conversational AI applications with natural-sounding voice.

Hume AI

Empathic AI platform for building voice interfaces that understand and respond to human emotions.

Multi-LLM Management

LiteLLM

Unified interface for calling 100+ LLM providers using OpenAI format with routing and fallbacks.

OpenRouter

Unified API for connecting and routing prompts across multiple LLM providers.

Portkey

AI gateway for prompt management, routing, and monitoring across multiple LLM providers with built-in observability.

TrueFoundry

AI Gateway by TrueFoundry for observability, cost tracking, and access control across LLM providers.

AWS Marketplace

Subscribe to Cerebras Inference through AWS with consolidated billing.

No-Code/Low-Code Platforms

Dify

No-code platform for building and deploying AI applications with visual workflows.

Flowise

Open-source drag-and-drop UI for building LLM flows and AI agents.

FlutterFlow

Visual development platform for building cross-platform AI-powered mobile apps.

Chatbot Platforms

Poe

Chatbot platform by Quora for accessing and comparing LLMs.