Getting your computer to tell you the gradient of a function, without resorting to finite difference approximation.
There seems to be a lot of stuff to know here; Infinitesimal/Taylor series formulations, and closely related dual number formulations, and even fancier hyperdual formulations. Reversemode, a.k.a. Backpropoagation, versus forwardmode etc. Computational complexity of all the above. But for special cases you can ignore most of this.
There is a beautiful explanation of the basics by Sanjeev Arora and Tengyu Ma.
You might want to do this for optimisation, batch or SGD, especially in neural networks, matrix factorisations, variational approximation etc. This is not news these days, but it took a stunningly long time to become common; see, e.g. Justin Domschke, Automatic Differentiation: The most criminally underused tool in the potential machine learning toolbox?.
See also symbolic mathematical calculators.
Software
can automatically differentiate native Python and Numpy code. It can handle a large subset of Python’s features, including loops, ifs, recursion and closures, and it can even take derivatives of derivatives of derivatives. It uses reversemode differentiation (a.k.a. backpropagation), which means it can efficiently take gradients of scalarvalued functions with respect to arrayvalued arguments. The main intended application is gradientbased optimization.
This is the most pythonic of the choices here; not as fast as tensorflow but simple to use and can differentiate more general things than Tensorflow.
autogradforward will mingle forwardmode differentiation in to calculate Jacobianvector products and Hessianvector products for scalarvalued loss functions, which is useful for classic optimization. AFAICT there are no guarantees about computational efficiency for these, but practically it’s often pretty good.
Another neuralnet style thing like tensorflow, but with dynamic graph construction as in autograd.
allows you to differentiate functions implemented as computer programs by using Algorithmic Differentiation (AD) techniques in the forward and reverse mode. The forward mode propagates univariate Taylor polynomials of arbitrary order. Hence it is also possible to use AlgoPy to evaluate higherorder derivative tensors.
Speciality of AlgoPy is the possibility to differentiate functions that contain matrix functions as +,,*,/, dot, solve, qr, eigh, cholesky.
Looks sophisticated, and indeed supports differentiation in an elegant way; but not so actively maintained, and the source code is hard to find.
 CasADi (Python, C++, MATLAB)
a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrixvalued computational graphs. It supports selfcontained Ccode generation and interfaces stateoftheart codes such as SUNDIALS, IPOPT etc. It can be used from C++, Python or Matlab
[…]CasADi is an opensource tool, written in selfcontained C++ code, depending only on the C++ Standard Library. It is developed by Joel Andersson and Joris Gillis at the Optimization in Engineering Center, OPTEC of the K.U. Leuven under supervision of Moritz Diehl. CasADi is distributed under the LGPL license, meaning the code can be used royaltyfree even in commercial applications.
Documentation is minimal; probably should read the source or the published papers to understand how well this will fit your needs and, e.g. which arithmetic operations it supports.
It might be worth it for such features as graceful support for 100fold nonlinear composition, for example. But the price you pay is a weird DSL that you must learn to use it.

ADOLC is a popular C++ differentiation library with python binding. Looks clunky from python but tenable from c++.

stan is famous for Monte Carlo, but also does deterministic optimisation using automatic differentiation. this is a luxurious option; But it is computationally expensive and ugly to invoke purely for the gradients unless you are using their inference loop, so it does not count as a general purpose autodiff library.

ad, which is based off uncertainties (and therefore python) also does it.

ceressolver, (C++), the google least squares solver, is pretty good at this although mostly focussed on leastsquares solutions to things.

Theano, (python) supports autodiff as a basic feature and has a massive user base.

Tensorflow (python, C++, go, java) is the same deal, has a massive user base plus the backing of Google.
FYI there is an interesting discussion of its workings in the tensorflow jacobians ticket request

Symbolic math packages such as Sympy, MAPLE and mathematica can all do actual symbolic differentiation, which is different again, but sometimes leads to the same thing. I haven’t tried Sympy or MAPLE, but Mathematica’s support for matrix calculus is weak.

autodiff
, which is usually referred to as audi for the sake of clarity, offers light automatic differentiation for MATLAB. 
juliadiff has implemented forward and reverse mode autodiff, plus verious other lesscommondly seen flavours such as dual numbers and hyperdual numbers.
Refs
 BPRS15: (2015) Automatic differentiation in machine learning: a survey. ArXiv:1502.05767 [Cs].
 BaPe14: (2014) Automatic Differentiation of Algorithms for Machine Learning. ArXiv:1404.7456 [Cs, Stat].
 Rall81: (1981) Automatic differentiation: techniques and applications. Berlin ; New York: SpringerVerlag
 Gile08: (2008) Collected Matrix Derivative Results for Forward and Reverse Mode Algorithmic Differentiation. In Advances in Automatic Differentiation (Vol. 64, pp. 35–44). Berlin, Heidelberg: Springer Berlin Heidelberg
 GrWa08: (2008) Evaluating derivatives: principles and techniques of algorithmic differentiation. Philadelphia, PA: Society for Industrial and Applied Mathematics
 MaDA15: (2015) Gradientbased Hyperparameter Optimization through Reversible Learning. In ICML (pp. 2113–2122).
 Neid10: (2010) Introduction to Automatic Differentiation and MATLAB ObjectOriented Programming. SIAM Review, 52(3), 545–563. DOI
 RuHW86: (1986) Learning representations by backpropagating errors. Nature, 323(6088), 533–536. DOI
 ADGH16: (2016) Learning to learn by gradient descent by gradient descent. ArXiv:1606.04474 [Cs].
 Amar98: (1998) Natural Gradient Works Efficiently in Learning. Neural Computation, 10(2), 251–276. DOI
 Neue18: (2018) Review of theory and implementation of hyperdual numbers for first and second order automatic differentiation. ArXiv:1801.03614 [Cs].
 FiAl11: (2011) The Development of HyperDual Numbers for Exact SecondDerivative Calculations. In 49th AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition. Orlando, Florida: American Institute of Aeronautics and Astronautics DOI
 CHBL15: (2015) The Stan Math Library: ReverseMode Automatic Differentiation in C++. ArXiv Preprint ArXiv:1509.07164.
 BaPS16: (2016) Tricks from Deep Learning. ArXiv:1611.03777 [Cs, Stat].