A novel smart film MP/BNC/ACN for real-time monitoring of fish freshness was developed using myofibrillar protein (MP) and bacterial nanocellulose (BNC) as film raw materials and anthocyanin (Lycium ruthenicum, ACN) as an indicator. Firstly, the film containing 1 % ACN (MP/BNC/ACN1) was found to have a moderate thickness (0.44 ± 0.01 mm) and superior mechanical properties (tensile strength (TS) = 8.53 ± 0.11 MPa; elongation at break (EB) = 24.85 ± 1.38 %) by determining the physical structure. The covalent, electrostatic, and hydrogen bonding interactions between anthocyanin and the film matrix were identified and confirmed by FT-IR spectroscopy (FTIR), X-ray diffraction (XRD), and scanning electron microscope (SEM) analysis. A comprehensive evaluation concluded that MP/BNC/ACN1 exhibited excellent trimethylamine (TMA) sensitivity (total color difference (ΔE), ΔETMA0-1000 = 4.47–31.05; limit of detection (LOD), LOD = 1.03) and UV stability (ΔE96h = 4.16 ± 0.13). The performance of the films in assessing fish freshness was evaluated, principal component analysis (PCA) and hierarchical cluster analysis (HCA) revealed that MP/BNC/ACN1 (ΔE2-10d = 16.84–32.05) could clearly distinguish between fresh (0–2 d), sub-fresh (4–6 d), and spoiled (8–10 d) stages of fish, which corresponded to the film colors of red, light red, and gray-black. In conclusion, this study addresses the limitation that intelligent films cannot visually discern real-time freshness during fish storage and provides a promising approach for real-time fish freshness monitoring.