With the rapid development of Internet technologies, the Internet makes infinite charms and enormous population and also makes e-commerce well developed. Mobile agents are mobile, personalized, autonomous, and adaptive. These qualities make mobile agents useful for the information-rich and communication-rich environment such as e-commerce. The common online shopping markets commerce sites have two kinds of main drawbacks: 1. Because of the different product data format in database and representation, it is difficult to exchange information between the two online markets. 2. Consumers must search and filter product information by browsing a lot of shopping sites and have to compare the product prices by themselves. 3. It's hard to accumulate consumer's loyalty. Therefore, we extend the e-commerce platform that developed by our agent-based e-commerce research group and build an agent-based consumer recommendation mechanism. By followed the mechanism, agents on behalf of consumer can trade in the e-commerce platform and record the consumer preference and produce the appropriate product recommend information according to consumer's preference.