Open-core and self-hosted. Start free, add governance as your team grows.
Pricing
Self-hosted and open core. Pay only for enterprise features.
À la carte modules for teams that want a single Enterprise feature without the full tier.
FAQ
Everything you need to know about getting started.
LiteLLM and Portkey route to models and bolt on plugins. MemBrain shares state across functions: threat detection scrubs PII before cache keys are computed, cached responses feed memory, memory enriches future prompts, all under one audit chain. The pipeline coupling is the whole point — it's not a collection of independent plugins.
No. MemBrain works as a drop-in proxy. Point your existing OpenAI or Anthropic SDK at the MemBrain gateway URL. For org-wide protection, deploy at the network level with a DNS override — no code changes, no agent installs, every AI tool covered.
OpenAI, Anthropic, and Ollama are supported natively. With the optional LiteLLM integration, you get access to 100+ models including Azure OpenAI, Google Gemini, AWS Bedrock, and more.
LLMs like GPT and Claude are the creative cortex — they generate language. But a real brain has memory (hippocampus), threat detection (amygdala), judgment (prefrontal cortex), and routing (thalamus). MemBrain provides these missing cognitive functions as software infrastructure. We call it a cognitive layer because it adds cognition around the model, not just a passthrough in front of it.
Yes. The Community tier is free forever and includes the core proxy, PII detection, dashboard, rate limits, budgets, caching, and full audit trail. Enterprise features require a license.
The Enterprise trial lasts 30 days with full access to every feature. No credit card required. After the trial, you can continue using the Community tier for free or upgrade.
Join the waitlist to get early access and product updates.
View Documentation