HanLP
Open-source NLP toolkit for local text analysis on Linux, macOS and Windows, with CPU support and a separate hosted REST API. Apache 2.0 licensed.
HanLP is a multilingual natural language processing toolkit for developers and researchers who need structured text analysis. Its native Python API runs models on your own hardware. The separate REST API sends text to a hosted server.
The local toolkit supports tasks such as word segmentation, part-of-speech tagging, named entity recognition, dependency and constituency parsing, semantic role labeling and semantic dependency parsing. Pretrained multitask models can combine several annotations in one call; separate task models and custom dictionaries let developers adapt a pipeline to their data. Available tasks and languages depend on the chosen model.
HanLP uses PyTorch and TensorFlow. It supports Linux, macOS and Windows and can run on a CPU, with GPU acceleration recommended for larger workloads. Install the native Python package with pip; downloaded model checkpoints then run locally. The README documents Python 3.6–3.10, so check dependency compatibility before using a newer interpreter.
The project also advertises summarization, style conversion, correction and other services through its hosted API. Those services should not be assumed to be included in the native package. HanLP code uses Apache 2.0; individual pretrained model terms may differ.
