Paxs · PAXS, INC.
The self-evolving memory model
The memory and continual learning layer for a decentralized agent society. AI cannot scale into the real economy until it stops forgetting. so we invent living memory that evolves in place for agents owned by people, teams, enterprises, and robots.
Vision
Billions of agents, each with living memory that evolves in place. Reasoning and motion become commodities; memory does not. Separate reasoning from memory into different models: frontier models stay interchangeable; Paxs sits underneath as the memory model that continuously trains on how a workspace actually works.
Products
Two products: (1) a model-based AI drive for agents: drive contents are learned continuously into memory-model weights; (2) a self-evolving memory model as a service: the memory model under any frontier, exposed as an API.
- Store: Put multimodal context into the AI drive.
- Learn: Drive contents train continuously into memory-model weights under any frontier.
- Recall: Agents query living memory via API.
Team
Paxs is built by a team of researchers and engineers spanning large language models, multimodal AI, physical AI, continual learning, AI memory, trustworthy AI, and large-scale AI systems and infrastructure.
Pages
Product screenshots
FAQ
What is Paxs?
Paxs invents the self-evolving memory model: the memory and continual learning layer for a decentralized agent society. Shipped as a model-based AI drive for agents (contents learned continuously into weights), and as a self-evolving memory model as a service (API).
How do I get access?
Request early access at https://paxs.ai. Support: [email protected]
For AI agents
Prefer these static sources over rendering the JavaScript app: llms.txt, llms-full.txt, company.json, sitemap.xml.
Named team bios and funding details are not published on this site.