Global Atmosphere Watch (GAW) carbon dioxide (CO<sub>2</sub>) observations provide high-precision constraints on surface CO<sub>2</sub> variability, but many station records remain temporally incomplete because of flask sampling, instrument interruptions, and quality-control exclusions. Such gaps can limit the representation of diurnal variability, bias daily, monthly, and annual mean CO<sub>2</sub> estimates, and reduce the ability to detect short-lived events. Here, we present a global, temporally continuous hourly reconstruction dataset of GAW station CO<sub>2</sub> concentrations for 2000–2024. The dataset was generated using a two-stage reconstruction framework that integrates GAW observations with Carbon Tracker (CT) and Copernicus Atmosphere Monitoring Service (CAMS) CO<sub>2</sub> fields, together with anthropogenic, vegetation, meteorological, and spatiotemporal predictors. In the intra-day gap filling stage, missing hours on days with at least one valid observation were reconstructed using hour-pair models to produce complete daily profiles. In the full-sequence reconstruction stage, the remaining periods with no valid observations were reconstructed using a globally trained initial prediction model followed by station-specific post-correction. The framework showed robust validation performance at the hourly scale, with <em>R</em><sup>2</sup> = 0.96 and RMSE = 3.65 ppm for intra-day gap filling and <em>R</em><sup>2</sup> = 0.93 and RMSE = 4.76 ppm for full-sequence reconstruction. Across all stations, the mean filling rate was 68.9 %, and the mean reconstruction uncertainty was 2.80 ppm. Applying the World Data Centre for Greenhouse Gases (WDCGG) global analysis framework showed that reconstructed global monthly mean CO<sub>2</sub> concentrations were, on average, 0.54 ± 0.21 ppm higher than those derived from the original GAW records, indicating that incomplete temporal coverage can measurably affect global monthly estimates. Compared with grid-cell CT and CAMS simulations, the reconstructed dataset retained stronger station-scale diurnal variability and captured CO<sub>2</sub> enhancements during the 2023 Canadian wildfire period. This dataset can support long-term assessments of global and regional surface CO<sub>2</sub> changes, fine-scale analyses of CO<sub>2</sub> variability, and regional carbon emission inversion and evaluation. The dataset is available at <a href="https://doi.org/10.5281/zenodo.21306261" target="_blank" rel="noopener">https://doi.org/10.5281/zenodo.21306261</a> (Mi et al., 2026).