
Praxos is an AI-driven data layer designed to enhance agent memory and improve the efficiency of AI agents. Initially founded as an insuretech startup, Praxos focuses on extracting structured data from complex documents, particularly in the insurance sector. The company has developed a comprehensive toolkit that supports various file types and custom ontologies, allowing users to create tailored data systems. With significant improvements in accuracy and reduced operational costs, Praxos positions itself as a leader in the AI agent space, offering solutions that adapt and learn over time, making it an attractive option for developers and businesses looking to leverage AI technology.

Praxos is an AI-driven data layer designed to enhance agent memory and improve the efficiency of AI agents. Initially founded as an insuretech startup, Praxos focuses on extracting structured data from complex documents, particularly in the insurance sector. The company has developed a comprehensive toolkit that supports various file types and custom ontologies, allowing users to create tailored data systems. With significant improvements in accuracy and reduced operational costs, Praxos positions itself as a leader in the AI agent space, offering solutions that adapt and learn over time, making it an attractive option for developers and businesses looking to leverage AI technology.
Product: Knowledge-graph + extraction + AI-powered retrieval (Intelligent Search) for AI agent workflows
Founding: Founded 2023 by Lucas Urbisaia and Soheil Sadabadi (Miami)
Funding (reported): Seed — Aug 2024 — $125,000 (lead: Y Combinator)
Developer offering: Python SDK, API keys, environments/knowledge graph primitives
Enterprise features: Usage-based pricing with enterprise tier offering VPC and on-prem deployments
AI agent state and memory, structured data extraction from complex documents (initial focus on insurance/insurtech workflows)
2023
Insurtech
125000.00 USD
“Y Combinator; Horizon”