Integrations
SambaNova integrations enable you to build and deploy AI applications faster and more efficiently. Connect seamlessly with your favorite frameworks, data sources, and infrastructure platforms to accelerate development and streamline your AI workflows.
Agent building and orchestration
Agno
Integrate with Agno to build AI agents.
Autogen
Build multi-agent applications with Autogen.
Camel-AI
Leverage Camel-AI to create communicative agents.
CrewAI
Orchestrate autonomous AI agents using CrewAI.
Semantic Kernel
Integrate AI services with Semantic Kernel.
Coding assistants
Cline
Command-line interface for LLMs.
Continue
Use Continue for AI-powered code editing.
VS Code AI Toolkit
Develop AI agents and apps using the lightweight VS Code extension.
Evaluation and monitoring
LM evaluation harness
Benchmark models with LM evaluation harness for reproducible, large-scale LLM evaluation.
Weave
Debug, evaluate, and improve LLM applications with real-time observability and experimentation.
LLM frameworks
AI Suite
Build and deploy AI applications with AI Suite.
Gradio
Create interactive AI demos with Gradio.
Haystack
Build production-ready LLM applications with Haystack.
Hugging Face
Use SambaNova models with Hugging Face tools.
LangChain
Build LLM applications with LangChain.
🚅 LiteLLM
LiteLLM
Standardize API calls across LLM providers with LiteLLM.
LlamaIndex
Use LlamaIndex to build AI applications.
Llama Stack
Deploy secure, production-ready LLM applications using Llama Stack.
Oumi
Create LLM-based applications with Oumi.
Vercel
Deploy LLM applications seamlessly on Vercel.
Low-code platforms
Dify
Build AI applications using Dify’s low-code platform.
Langflow
Design and manage LLM workflows with Langflow.
n8n
Automate your AI workflows with n8n.
Real-time voice
Hyperscalers
AWS Marketplace
Deploy SambaNova via AWS Marketplace.
AWS PrivateLink
Secure SambaNova access through AWS PrivateLink.
Tool and Browser Use
Browser Use
Run SambaNova in your browser for seamless access.
Instructor
Generate structured outputs using Instructor.