Lethe
GetLLMYour AI memory layer — it sits on top of every large model and remembers what you've said, the files you've shared, and the questions you care about, so continuity isn't lost when the underlying model changes.
The Memory conversation workspace and open API are in active development. We'll notify you via your registered email when they launch.
While you wait, you can create an API Key and start using GetLLM's unified access from Claude Code, Codex, Cursor or any other dev tool.
The three pillars of Memory
What you said to Claude today carries over to GPT tomorrow and to a local model the day after. Your context belongs to you, not to a single model.
Upload notes, papers, contracts, archives — Memory organizes them into a retrievable knowledge layer with precise citations, so the AI has actually "read your files."
A GraphRAG-backed domain knowledge graph that weaves authoritative materials and their relations into traceable answer chains, each conclusion citing its source. The first verticals will be announced on launch day.
Memory isn't just a conversation window. A complete Memory / Documents / Knowledge API trio opens to every GetLLM user — embed this memory capability in your own apps, home devices, or third-party tools. Your data stays under your account; migration, export and deletion are always your call.
Live — call Claude / GPT / Gemini and others with one key and one SDK.
In development — cross-model continuity, personal document understanding, vertical industry knowledge, open API.
The two layers are billed and used independently. Developers already on the Gateway need no changes; users who want Memory can opt in after launch without affecting existing API keys.