MemLibMemLib

Supported Providers

LLM and embedding providers supported by MemLib

Overview

MemLib supports multiple AI providers for both LLM (text generation) and embedding (vector generation). You configure your providers when creating a project in the dashboard.


LLM Providers

Used for fact extraction, conflict resolution, context synthesis, and consolidation.

Google Gemini

ModelContext WindowDefault
gemini-2.0-flash1M tokens
gemini-1.5-flash1M tokens
gemini-1.5-pro2M tokens

API Key: Get from Google AI Studio

OpenAI

ModelContext WindowDefault
gpt-4o128K tokens
gpt-4o-mini128K tokens
gpt-4-turbo128K tokens

API Key: Get from OpenAI Platform

Anthropic

ModelContext WindowDefault
claude-4-sonnet200K tokens
claude-3.5-haiku200K tokens

API Key: Get from Anthropic Console

Mistral

ModelContext WindowDefault
mistral-large-latest128K tokens
mistral-small-latest128K tokens

API Key: Get from Mistral Console

Groq

ModelContext WindowDefault
llama-3.3-70b-versatile128K tokens
gemma2-9b-it8K tokens

API Key: Get from Groq Console

xAI

ModelContext WindowDefault
grok-2128K tokens
grok-2-mini128K tokens

API Key: Get from xAI Console

Cohere

ModelContext WindowDefault
command-r-plus128K tokens
command-r128K tokens

API Key: Get from Cohere Dashboard

OpenRouter

ModelDescriptionDefault
AnyAccess any model via OpenRouter

API Key: Get from OpenRouter

OpenRouter lets you use models from any provider through a single API. Useful if you want to experiment with different models without managing multiple API keys.


Embedding Providers

Used for generating vector embeddings for semantic search.

Google Gemini

ModelDimensionsDefault
text-embedding-004768

OpenAI

ModelDimensionsDefault
text-embedding-3-small1536
text-embedding-3-large3072

Cohere

ModelDimensionsDefault
embed-english-v3.01024
embed-multilingual-v3.01024

Mistral

ModelDimensionsDefault
mistral-embed1024

Voyage

ModelDimensionsDefault
voyage-31024
voyage-3-lite512

API Key: Get from Voyage AI


Choosing a Provider

For Best Quality

  • LLM: OpenAI GPT-4o or Anthropic Claude 4 Sonnet
  • Embedding: OpenAI text-embedding-3-large

For Best Speed

  • LLM: Groq (LLaMA 3.3 70B) or Google Gemini 2.0 Flash
  • Embedding: Google Gemini text-embedding-004

For Lowest Cost

  • LLM: Google Gemini 2.0 Flash or Groq
  • Embedding: Google Gemini text-embedding-004

For Best Multilingual Support

  • Embedding: Cohere embed-multilingual-v3.0

Custom Providers

If your provider is OpenAI-compatible (most are), you can use it by selecting OpenRouter as the provider and configuring a custom base URL in your project settings.

On this page