Your agents keep forgetting, and your token bill pays for it
Open a fresh session with any AI agent and watch what it does first. It re-reads. The same project background, the same file structure, the same "here is what we decided last time," pulled back into the context window from zero. It has no memory of yesterday's work, so it rebuilds the whole world before it can help you. And you pay for every one of those tokens, every single time.
That cost is quiet because it hides inside what looks like normal usage. A long-running project can burn more tokens re-establishing context than it spends on the actual task. Multiply that by every session, every teammate, and every connected tool, and the bill climbs for a reason that has nothing to do with the work getting done.
The bottleneck was never the agents
We (Nils and Florian) spent a long time assuming the models were the constraint. They are not. The models are good. What breaks is everything around them: the connection to your tools, and the context that evaporates the moment a session ends. An agent that cannot remember is an agent you have to re-brief forever.
So the real problem is a memory problem. If context survived between sessions, the agent would stop paying the re-reading tax, and it would stop asking you the same questions it asked last week.
A memory layer in front of your MCP servers
That is what we have been building. Tulimoa is an MCP Gateway that sits in front of your MCP servers and remembers. You connect your tools once, and the gateway holds context across sessions with two simple moves: remember to store what matters, and recall to bring it back. The agent stops rebuilding the world from scratch, so it stops re-reading (and re-paying) for context it already had.
This is the brand core, not a side feature. The MCP Gateway that doesn't forget. The memory layer that shrinks your token bill.
A few concrete things that are live today:
- One endpoint in front of multiple connected tools, so an agent reaches everything through a single OAuth connection.
- Usage analytics, so you can actually see where the tokens go.
- Teams, so a group can share one pool of credits, memory, and connected agents.
- Everything runs EU-hosted in Frankfurt, GDPR-first, with a dashboard that follows your language in English or German.
Honestly, it is an early beta
We are not going to dress this up. Tulimoa is early. There are rough edges, and we are shipping fixes constantly. It is free to use during the beta, with 25,000 credits a month. Paid plans come later (via LemonSqueezy), and even then the intent is to keep the free tier genuinely useful.
If your agents keep forgetting, and your token bill keeps climbing for context you have already paid to load, come try the gateway. Connect a tool, remember something, close the session, open a fresh one, and recall it. That loop is the whole idea, and it is the part we most want your feedback on.