Skip to main content
MemWire never calls an LLM internally. Memory storage, recall, and search are pure vector operations. You choose the LLM and MemWire supplies the context to inject into it. 
result = memory.recall("How should I format my answers?", user_id="alice")

# Inject into any LLM prompt
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
]
if result.formatted:
    messages.append({"role": "system", "content": f"Memory context:\n{result.formatted}"})
messages.append({"role": "user", "content": "How should I format my answers?"})

​
Supported providers

OpenAI

GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo

Azure OpenAI

GPT-4o, GPT-4 Turbo deployed on Azure

Anthropic

Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku

Ollama

Llama 3, Mistral, Gemma and any locally hosted model

Google Gemini

Gemini 2.0 Flash, Gemini 1.5 Pro

Any OpenAI-compatible API

Together AI, Groq, Mistral, DeepSeek