LLM Providers
Connect to any major language model provider — cloud, local, or through a gateway.Native Providers
OpenAI
GPT-4o, GPT-4, GPT-3.5 via Chat Completions API.
OpenAI Responses
OpenAI Responses API with built-in tools.
Anthropic
Claude 4, Claude 3.5 Sonnet, Haiku & more.
Google Gemini
Gemini Pro, Gemini Flash & more.
Mistral
Mistral Large, Medium, Small & Codestral.
Cohere
Command R, Command R+ models.
Grok
xAI Grok models via LiteLLM.
xAI
xAI native SDK for Grok models.
Moonshot AI
Moonshot AI (Kimi) models.
Cloud Providers
Azure OpenAI
Azure-hosted OpenAI models.
AWS Bedrock
Claude, Llama, Titan via AWS Bedrock.
HuggingFace
HuggingFace Inference Endpoints.
Heroku
Heroku Inference API.
OVHcloud
OVHcloud AI Endpoints.
Local Providers
Ollama
Run models locally with Ollama.
vLLM
High-throughput local LLM serving.
LM Studio
Local models via LM Studio GUI.
Model Gateways
Groq
Ultra-fast LPU inference.
OpenRouter
Unified access to 100+ models.
LiteLLM
Unified LLM proxy gateway.
NVIDIA NIM
NVIDIA cloud-based inference.
Together AI
Open and hosted models.
SambaNova
SambaNova AI platform.
Cerebras
Cerebras fast inference API.
GitHub Models
GitHub Models marketplace.
Vercel
Vercel AI Gateway.
Outlines
Structured generation for local models.
Vector Stores
Store and retrieve embeddings with your preferred vector database for RAG.Chroma
Open-source embedding database.
Qdrant
High-performance vector search.
Pinecone
Managed vector database.
Milvus
Scalable vector database.
PGVector
Vector search in PostgreSQL.
FAISS
Facebook AI Similarity Search.
Weaviate
AI-native vector database.
SuperMemory
SuperMemory vector store.
Embedding Providers
Generate vector embeddings for your knowledge base documents.OpenAI
text-embedding-3-small/large.
Azure OpenAI
Azure-hosted embedding models.
Gemini embedding models.
AWS Bedrock
Titan & Cohere embeddings.
HuggingFace
Open-source embedding models.
FastEmbed
Lightweight, fast embeddings.
Ollama
Local embedding models.
Document Loaders
Load and parse documents from various file formats into your knowledge base.PyPDF
Standard PDF loader.
PdfPlumber
Advanced PDF table extraction.
PyMuPDF
Fast PDF processing.
Docling
IBM’s advanced document parser.
DOCX
Microsoft Word documents.
CSV
Comma-separated values.
JSON
JSON structured data.
Markdown
Markdown documents.
HTML
HTML web pages.
XML
XML documents.
YAML
YAML configuration files.
Text
Plain text files.
Text Splitters
Split documents into optimal chunks for embedding and retrieval.Recursive
Smart recursive splitting.
Semantic
Meaning-based splitting.
Agentic
AI-powered splitting.
Character
Character-based splitting.
Markdown
Markdown-aware splitting.
HTML
HTML tag-aware splitting.
JSON
JSON structure-aware splitting.
Python
Python code-aware splitting.
Memory Storage
Persistent storage backends for agent memory and conversation history.In-Memory
Fast, ephemeral storage.
JSON
File-based JSON storage.
SQLite
Lightweight local database.
PostgreSQL
Production-grade relational DB.
Redis
In-memory data store.
MongoDB
Document-oriented database.
Mem0
AI-native memory layer.
Async Storage
Async SQLite
Async SQLite storage.
Async PostgreSQL
Async PostgreSQL storage.
Async MongoDB
Async MongoDB storage.
Async Mem0
Async Mem0 storage.
Storage Tables Reference
Detailed comparison of all storage backend features and capabilities
Interfaces
Deploy your agents on messaging platforms and communication channels.Slack
Deploy agents as Slack apps.
Serve agents via WhatsApp.
Telegram
Host agents as Telegram bots.
Gmail
Automated email processing.
Tracing & Observability
Monitor, trace, and debug your agent runs with observability platforms.Tools — Search
Web search tools your agents can use to find information.DuckDuckGo
Privacy-focused web search.
BochaSearch
AI-optimized search API.
Tavily
Search API built for AI agents.
Tools — Data
Data retrieval tools for financial and structured data.Tools — Scraping
Web scraping and data extraction toolkits.Tools — Model Provider
Native tools from model providers (OpenAI, Anthropic, etc.).Web Search
Provider-native web search.
Web Fetch
Fetch content from URLs.
File Search
Search through uploaded files.
Code Execution
Execute code in sandbox.
Image Generation
Generate images with DALL·E.
URL Context
Extract context from URLs.
MCP Server
Connect MCP servers as tools.
Supported Providers
See which model providers support which native tools
Browser & Computer Use
Enable agents to interact with websites and desktop applications.Browser Use
Navigate sites, extract data, fill forms.
Computer Use
Mouse and keyboard control like a human.