Exploring the relations between streamflow and large-scale atmospheric circulation systems can assist in identifying potentially useful indicators for the modeling of hydrological processes. With the help of ensemble empirical mode decomposition and the wavelet analysis method, this research explored streamflow variations and its links to large-scale atmospheric circulation indices during 1960–2012 in the Three Rivers Headwater Region (TRHR). A steady increasing trend was detected in the streamflow of the source region of Yangtze River (SYR), and a steady decreasing trend was detected in the streamflow of the source region of Lancang River (SLR). The streamflow of the source region of Yellow River (SYeR) had an increasing trend in the early years of the study period and subsequently exhibited a decreasing trend. The Tibetan Plateau monsoon (TPM), Arctic Oscillation (AO), and South Asia monsoon (SAM) are the key factors influencing streamflow changes in the SYR, SYeR, and SLR, respectively. At interannual time-scale variation with the period of about 3–9 years, an antiphase relationship exists between SYR streamflow and TPM indices, while in-phase relationships are detected between SYeR (SLR) streamflow and AO (SAM) indices.