Utilizing the potential of Static Random-Access Memory (SRAM), In-Memory Computing has surfaced as available approach to tackle the computational and energy-efficiency issues. An overview of memory computing's energy-efficient SRAM for AI applications is given in this paper. When compared to traditional SRAM, memory technologies provide benefits in the form of reduced leakage power, increased durability, and enhanced reliability, which supports long-term and reliable AI hardware implementation. To sum up, memory computing with energy-efficiency the SRAM offers available solution to the computational and energy issues in AI hardware design. SRAM-build on In- Memory Computing has the potential to completely change the field of the AI computing by utilizing cutting-edge architectural improvements and newly developed memory technologies to create more effective and scalable AI systems for a wide range of application areas. SRAM array based on 10 T SRAM is constructed in 180-nm SCL technique to examine the advocated IMC macro architecture's functionality and performance. In this paper we have used supply voltage of 1.8 V, Array size of 136 × 32, energy efficiency obtained 1 V and achieves an area efficiency of 65.2%.