If you want to use a program, currently not contained in the OpenWrt repository, you probably won't find a binary compiled for your CPU. Provided that it is released as open source, you can download the code and compile it using the OpenWrt Buildroot.
Note that not every code is compilable for every CPU architecture. Also performance and available RAM on embedded systems is limited compared to ordinary computers.
staging_dir/toolchain-architecture_gcc-compilerver_uClibc-libcver/bin/ directoryPATH environment variable:PATH=$PATH:(your toolchain/bin directory here)export PATHSTAGING_DIR environment variable to the above toolchain dir and export it:STAGING_DIR=(your toolchain directory here)export STAGING_DIR--build=architecture-unknown-linux-gnu --host=architecture-openwrt-linux-uclibc (for example: ./configure --build=x86_64-unknown-linux-gnu --host=mips-openwrt-linux-uclibc)./config.guess to get the --build= option.'checking whether we are cross compiling... yes' is yes.CC and LD environment variables (usually not needed if GNU configure was used)make CC=architecture-openwrt-linux-uclibc-gcc LD=architecture-openwrt-linux-uclibc-ldfind -iname *program*file program to confirm cross-compiling was successful. CFLAGS and LDFLAGS to point to the staging_dir/target-architecture_uClibc-libcver/usr/include and .../usr/lib directoriesmake menuconfig. [Advanced configuration options→Toolchain Options→Build gdb]./scripts/remote-gdb
When compilation is finished, copy the resulting binary and related libraries to the target device to test it.
It might be necessary to set LD_LIBRARY_PATH on the target to point the binary to libraries in non-standard locations.
If the program works well enough, you maybe want to build a real package for the opkg package manager and make it easily accessible for everyone out there. See Creating your own packages and Using Dependencies for further information on that.