The provision of agricultural market information has demonstrated potential to improve the incomes of smallholder farmers who comprise over 80% of India's agricultural population. The scarcity of accurate price information, however, leads farmers to accept suboptimal economic outcomes.

By eliminating information asymmetries, the provision of actionable information theoretically reduces costs of price discovery and increases farmers' bargaining power. The resulting price convergence increases market efficiency and reduces volatility. Evaluations of market information services, however, show mixed results. In addition to market barriers, technical and language illiteracy undermine the success of market information services in low-income countries. In this paper, we present Mobile Mandi -- a mobile application that delivers daily retail prices of 22 essential commodities at 157 markets sourced from the Government of India's Department of Consumer Affairs. We present next-day price forecasts by training long short-term memory (LSTM) models on a univariate time series dataset of daily crop prices over ten years and benchmark performance against a baseline persistence model. We design the user interface for low-literate users and provide a conversational agent to facilitate information dissemination in English, Hindi, Punjabi and its transliterations. Noting the prevalent use of the WhatsApp messaging service in India, we integrate the service for seamless interoperability.