OpenNARS for Applications

# OpenNARS for Applications (ONA) **Full title:** Autonomy through Real-Time Learning and OpenNARS for Applications **Author:** Patrick Hammer **Year:** 2021 **Type:** PhD thesis / dissertation (Temple University; advisor Pei Wang) **Source:** ProQuest — [dissertation record](https://search.proquest.com/openview/1bece396f7f14b2740f23e68995f1435/1?pq-origsite=gscholar&cbl=18750&diss=y) ## Abstract > This work includes an attempt to enhance the autonomy of intelligent agents via real-time learning. In nature, the ability to learn at runtime gives species which can do so key advantages over others. While most AI systems do not need to have this ability but can be trained before deployment, it allows agents to adapt, at runtime, to changing and generally unknown circumstances, and then to exploit their environment for their own purposes. To reach this goal, in this thesis a pragmatic design (ONA) for a general-purpose reasoner incorporating Non-Axiomatic Reasoning System (NARS) theory is explored. The design and implementation is presented in detail, in addition to the theoretical foundation. Then, experiments related to various system capabilities are carried out and summarized, together with application projects where ONA is utilized: a traffic surveillance application in the Smart City domain to identify traffic anomalies through real-time reasoning and learning, and a system to help first responders by providing driving assistance… *(abstract truncated in source catalog)* ## Relevance to Hyperon **OpenNARS for Applications (ONA)** is the practical NARS reference implementation and the foundational engineering source for the Non-Axiomatic Reasoning work across the Hyperon ecosystem. It operationalizes NARS under the Assumption of Insufficient Knowledge and Resources (real-time, resource-bounded reasoning + online learning), and is the lineage behind the NAL rulesets re-implemented in MeTTa (see MeTTa-NARS Deep Dive), the Claw agents' NAL layers (mettaclaw / metta-nars / PeTTa-OpenPSI, verified in the Cross-Org sweeps), and the PLN↔NARS comparison work. It complements **Pei Wang's** foundational NARS theory (Non-Axiomatic Logic, 2013; *Rigid Flexibility*, 2006) — the canonical books that define NAL/NARS itself. *Ingested 2026-06-24 from the SNET — Research Publication Categorization catalog (the lone `Type=BOOK` entry), to close the NARS foundational-coverage gap identified in WS9 of the Wiki Finalization Meta-Plan.*