TensorFlow is a machine learning library created by the Brain Team researchers at Google and now open sourced under the Apache License 2.0. TensorFlow is detailed in the whitepaper TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. The source code can be found on Google Git.
TensorFlow is a tool for writing and executing machine learning algorithms. Computations are done in a data flow graph where the nodes are mathematical operations and the edges are tensors (multidimensional data arrays) that are exchanged between nodes. An user constructs the graph and writes the algorithms that executed on each node. TensorFlow takes care of executing the code asynchronously on different devices, cores, and threads.
TensorFlow runs on CPU and GPUs on the desktop, server or mobile devices. It can be containerized with Docker to be deploy in the cloud. The version that is open sourced runs on single machines, not on clusters.
TensorFlow has a complete Python API and C++ interface for building and executing graphs. It also has a C-based client API. Google invites the community to write interfaces in other languages, the most probably being Lua, R, Java, Go and JavaScript.
Google considers the library is not final and will continue to improve it. They will make public some of the actual implementations they have created.
TensorFlow is used by Google for GMail (SmartReply), Search (RankBrain), Pictures (Inception Image Classification Model), Translator (Character Recognition), and other products.