Artificial synapses are the key building blocks for low‐power neuromorphic computing that can go beyond the constraints of von Neumann architecture. In comparison with two‐terminal memristors and three‐terminal transistors with filament‐formation and charge‐trapping mechanisms, emerging electrolyte‐gated transistors (EGTs) have been demonstrated as a promising candidate for neuromorphic applications due to their prominent analog switching performance. Here, a novel graphdiyne (GDY)/MoS2‐based EGT is proposed, where an ion‐storage layer (GDY) is adopted to EGTs for the first time. Benefitting from this Li‐ion‐storage layer, the GDY/MoS2‐based EGT features a robust stability (variation < 1% for over 2000 cycles), an ultralow energy consumption (50 aJ µm−2), and long retention characteristics (>104 s). In addition, a quasi‐linear conductance update with low noise (1.3%), an ultrahigh Gmax/Gmin ratio (103), and an ultralow readout conductance (<10 nS) have been demonstrated by this device, enabling the implementation of the neuromorphic computing with near‐ideal accuracies. Moreover, the non‐volatile characteristics of the GDY/MoS2‐based EGT enable it to demonstrate logic‐in‐memory functions, which can execute logic processing and store logic results in a single device. These results highlight the potential of the GDY/MoS2‐based EGT for next‐generation low‐power electronics beyond von Neumann architecture. A novel graphdiyne (GDY)/MoS2‐based electrolyte‐gated transistor using GDY as a Li‐ion‐storage layer is proposed, which features robust stability and flexibility, an ultralow energy consumption, a long retention time, a quasi‐linear weight update with low noise, an ultrahigh Gmax/Gmin ratio, and an ultralow readout conductance. This GDY/MoS2‐based EGT has demonstrated its potential in applications of neuromorphic computing and in‐memory computing.