Abstract: Foreign Function Interface (FFI) is a fundamental method to invoke interfaces provided in another programming languages. Focusing on the issue that huge amount of manual coding was required when using FFI, Automatic a Foreign function Interface Generation (AFIG) was proposed. A reverse source code analysis technique based on the abstract syntax tree was employed by AFIG to accurately retrieve the multilingual intermediate representation from library binaries, in which function interface information was described. Based on the representation, the multilingual conversion rule matrix could be utilized by different platform code generators to automatically generate FFI codes for various platforms without handcrafting. To further reduce generation time usage, a dependency analysis-based task aggregation strategy was proposed, by which tasks with dependencies were consolidated as monolithic ones. Hence, blocking and deadlocks were efficiently eliminated, and load balancing and scalability on multi-core systems were achieved, accordingly. Experimental results indicate that a reduction of 98.14% for FFI manual codes and 41.95% for testing codes are achieved. Compared to SWIG, AFIG can further reduce development cost by 61.27% under the same task. Besides, the code generation mechanism is proven to be scalable because experimental results indicate a linear time reduction as the number of central processing unit cores increases.