Glossary
The terms behind company AI, explained
Each entry explains the idea first, in general, and says where Memtro stands in relation to it last and briefly. Written for people deciding what to build or buy, not for people who already know.
- What is MCP (Model Context Protocol)?MCP is an open protocol that lets an AI application call tools and read data from any server that speaks it. What a server exposes, how the transports work, who supports it, and what to watch.Read the entry →
- What is an LLM gateway?An LLM gateway is one endpoint in front of many model providers: it holds the keys, routes each request, falls back when a provider fails, and logs and caps what is spent. What to expect from one and where it stops.Read the entry →
- What is agent memory?Agent memory is what an AI agent keeps between turns and sessions beyond its context window: facts, preferences, history. The kinds of memory, how it is built, the hard problems, and why a shared memory differs from a personal one.Read the entry →
- What is an OpenAI-compatible API?An OpenAI-compatible API accepts the request and response shapes of OpenAI's API, so any client built for OpenAI works by changing a base URL and a key. What compatibility covers, where it stops, and the other wire formats.Read the entry →
- What is model routing?Model routing chooses which model answers each request automatically, by difficulty, cost or capability, with fallbacks when one fails. Ladders, classifiers, cascades, and what goes wrong.Read the entry →
- What is knowledge graph memory?Knowledge graph memory stores what an AI knows as entities, relations and dated facts rather than only text chunks and vectors. What that makes possible, entity resolution, bitemporal facts, and how it combines with vector retrieval.Read the entry →
See the ideas running
Connect one system, point a client you already use at Memtro, and ask it a question you know the answer to. Seven days free.