Self-host for $10/mo (first month free), or let us host it for a fraction of what Mem0, Supermemory, and Letta charge. Same persistent memory. A fraction of the cost.
Two completely different setups for two different kinds of users. Pick the one that fits how you work.
Need a custom volume deal or compliance requirements? Email us.
The expensive tools run knowledge graphs on GPU clusters. ChatSorter uses importance scoring + a small local LLM, simpler architecture, same persistent memory, dramatically lower cost.
| Tool | Architecture | Per-operation cost | Your API token savings | Data location |
|---|---|---|---|---|
| Mem0 | Knowledge graph + cloud LLM | ~$0.002 per memory op | Yes | Their servers |
| Supermemory | Vector DB + cloud compute | Cloud pricing | Partial | Their servers |
| Letta | Knowledge graphs + agents | High compute cost | Yes | Their servers |
| ChatSorter | Local LLM + importance scoring | $0.00 / op (self-hosted) | Up to 93% fewer tokens | Your server |
You install the chatsorter-local pip package, drop a license key into chatsorter.json, and run it. It starts a local API server on your machine. Your chatbot calls localhost instead of our servers. Conversation data never leaves your infrastructure — the only outbound connection is a brief weekly license check against api.chatsorter.com to confirm your subscription is active.
Anything that can run Python and Ollama. A $5/month VPS handles low-to-medium traffic fine. A standard developer laptop handles testing and development. The default model (qwen2.5:3b) runs on CPU if you don't have a GPU, though a GPU makes summarization faster.
At message 500, a raw conversation history sent to your LLM is ~25,000 tokens. ChatSorter returns up to 10 compressed summaries and 20 extracted facts, about 1,850 tokens. That's a 93% reduction in input tokens on every request. The longer the session, the bigger the saving. Full calculation on the homepage.
Yes, anytime. Start a Local trial from the plans page, install the package, and point your integration at localhost instead of api.chatsorter.com. The API surface is identical — same endpoints, same JSON format — so switching is usually a one-line config change.
It keeps running as long as your subscription is active. The server does a quick license check once a week — if it can't reach us (say, your machine is offline), it gives you a 7-day grace period before it pauses. Cancel anytime from the dashboard and it stops at the end of your billing cycle.
Your compute is free for us to serve, which is why it's so cheap. The $10/mo covers continued development, the hosted license verification endpoint, and email support. The first month is always free so you can try it properly before committing. If you cancel, all your data stays on your machine — we never had it to begin with.
Self-host with a free trial, or start free in the cloud and upgrade as you grow.