MCPcopy Create free account
hub / github.com/dmlc/treelite

github.com/dmlc/treelite @4.7.0

Chat with this repo
repository ↗ · DeepWiki ↗ · release 4.7.0 ↗ · + Follow
823 symbols 2,489 edges 113 files 250 documented · 30% updated 15d ago4.7.0 · 2026-03-06★ 82318 open issues

Browse by type

Functions 686 Types & classes 133 Endpoints 4
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

Treelite

Coverage tests Documentation Status codecov GitHub license PyPI version Conda Version

Documentation | Installation | Release Notes | Acknowledgements |

Treelite is a universal model exchange and serialization format for decision tree forests. Treelite aims to be a small library that enables other C++ applications to exchange and store decision trees on the disk as well as the network.

Core symbols most depended-on inside this repo

Shape

Method 350
Function 336
Class 120
Enum 13
Route 4

Languages

C++74%
Python26%
C1%

Modules by API surface

include/treelite/tree.h45 symbols
src/model_loader/detail/xgboost_json/delegated_handler.h43 symbols
src/model_loader/sklearn.cc37 symbols
include/treelite/detail/serializer_mixins.h35 symbols
python/treelite/model.py34 symbols
src/model_loader/xgboost_legacy.cc30 symbols
src/model_loader/detail/xgboost_json/delegated_handler.cc29 symbols
src/serializer.cc28 symbols
src/model_builder/detail/json_parsing.h28 symbols
src/model_loader/detail/xgboost_json/sax_adapters.cc27 symbols
src/model_builder/model_builder.cc21 symbols
python/treelite/model_builder.py21 symbols

For agents

$ claude mcp add treelite \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

Ask about this repo answers extend the page