Self-Hosted LLM Infrastructure

The memory engine for AI agents - knowledge graph + vector memory in one self-contained container.

The LLM app platform - visual builder, RAG, agents, observability - the catalogue’s heaviest stack, shipped honestly.

Visual builder for LLM apps and agents - 100+ integrations, embeddable chat widgets, no prediction caps.

Open-source LLM observability - tracing, evals, prompt management - the full v3 stack with no per-unit metering.

The MemGPT agent server - agents live server-side with self-editing persistent memory.

One OpenAI-compatible gateway for every LLM provider - virtual keys, budgets, spend tracking - with no percentage fee.

Run open LLMs behind a simple API - llama, mistral, qwen. The local-model server (GPU recommended).

The self-hosted AI chat workspace - any model behind one UI, RAG over your documents, no per-seat pricing.

LLM tracing, evals, and a prompt playground in one container - the lightweight start to LLM observability.

A self-hosted embeddings API on CPU - bge-small in 512 MB, OpenAI-compatible, zero per-token bills.