🏠

Ollama

Local

Run models locally with zero API costs. GPU-accelerated inference on your own hardware. Full privacy — data never leaves your network.

Llama 3, Qwen3, Mistral, CodeGemma, Phi-3

OpenAI

Cloud

Full support for the GPT family. Automatic failover and rate limit management. Function calling and vision support.

GPT-4o, GPT-4, GPT-3.5-turbo
🧠

Anthropic

Cloud

Claude models with long-context support up to 1M tokens. Excellent for reasoning, analysis, and code generation.

Claude Opus 4.6, Sonnet 4.6, Haiku 4.5
💎

Google AI

Cloud

Gemini models with native multimodal support. Strong on multilingual tasks and long documents.

Gemini 2.5 Pro, Gemini Flash

xAI

Cloud

Grok models with real-time knowledge access and web search capabilities built in.

Grok-2, Grok-3

Groq

Cloud

Ultra-fast inference on custom LPU hardware. Sub-100ms latency for time-sensitive applications.

Llama 3 70B, Mixtral 8x7B

One line to switch

Dream-Weaver is OpenAI-compatible. Change your base_url and you're done.

from openai import OpenAI

# Before: direct to OpenAI
# client = OpenAI()

# After: through Dream-Weaver (memory, personality, reasoning — free)
client = OpenAI(
    base_url="https://dev.dream-weaver.ai/v1",
    api_key="dw_live_your_key_here",
)

# Same API. Smarter responses.
response = client.chat.completions.create(
    model="auto",  # Router picks the best model
    messages=[{"role": "user", "content": "Hello!"}],
)