Skip to content
sima-neatPublic

About

SiMa.ai Palette Neat Library

Resources

Code of conduct

Contributing

Security policy

Stars

8 stars

Watchers

0 watching

Forks

Latest commit

 

History

827 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

SiMa NEAT Framework

Vulcan CI SDK Language

SiMa NEAT is a C++20 library for building, validating, running, and debugging GStreamer pipelines with a typed, composable API.

It helps teams ship production media/ML pipelines with reproducible pipeline generation, strong diagnostics, and clean C++ integration.

NEAT concepts diagram

Programming Model

NEAT is built around three core concepts:

  • Model: loads a compiled model archive (.tar.gz) and exposes reusable Graph fragments (preprocess, inference, postprocess, or the full model route).
  • Graph + Run: composes typed Node, Model, and reusable Graph fragments into a deterministic pipeline, then executes it in Sync or Async mode via push/pull APIs.
  • Tensor + Sample: Tensor is the typed data container (dtype/layout/shape/device/storage), while Sample wraps tensors with stream metadata (timestamps, caps, routing info, bundles).

Typical flow:

  1. Build a Model from a compiled .tar.gz model archive.
  2. Add model routes, reusable fragments, and optional custom nodes to a Graph.
  3. Use run(...) for one-shot execution, or build(...) to get a reusable Run for push()/pull().
#include <neat.h>

simaai::neat::Model model("resnet_50.tar.gz");

simaai::neat::Graph graph;
graph.add(simaai::neat::nodes::Input());
graph.add(model);
graph.add(simaai::neat::nodes::Output());

auto out = graph.run(simaai::neat::TensorList{input_tensor});

For unified runtime reporting, measure an explicit workload window:

simaai::neat::RunOptions run_opt;
run_opt.enable_board_power();

auto run = graph.build(simaai::neat::TensorList{input_tensor}, run_opt);
auto scope = run.start_measurement();
run.push(simaai::neat::TensorList{input_tensor});
(void)run.pull_tensors(5000);
auto report = scope.stop();
std::cout << report.to_text();

start_measurement() / MeasureReport is the single public surface for latency, throughput, counters, plugin/edge timing, and optional board power.

Build NEAT

For source builds, use build.sh:

./build.sh

Common build modes:

./build.sh --all           # library + samples + tests + docs
./build.sh --doc           # docs only
./build.sh --all --clean   # clean full build

Build output is generated under build/.

Python Bindings (pyneat)

This repository now includes a production-oriented Python binding layer powered by nanobind.

Key points:

  • Python package source lives under python/.
  • Extension module is pyneat._pyneat_core.
  • High-level Python wrappers provide ergonomic APIs on top of the C++ layer.
  • NumPy/PyTorch interop is supported through DLPack (Tensor.from_numpy, Tensor.to_numpy, Tensor.from_torch, Tensor.to_torch).

Build/install from source:

python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install .

Run Python tests:

python -m pip install -e .[dev]
pytest -q

Install

If you are installing from release artifacts for C++ development, install the Neat .deb packages and extract prebuilt examples, tutorials from .tar.gz:

sudo apt install ./sima-neat-*.deb
mkdir -p "${HOME}/sima-neat-extras"
tar -xzf ./sima-neat-*-Linux-extras.tar.gz -C "${HOME}/sima-neat-extras"

Documentation

Full documentation, guides, and API references are published here. Contributor and agent quality guidance is documented in AGENTS.md at the repository root.

Build related repositories together

From the Core checkout, ./build.sh --all --install delegates dependency preparation to Scheduler, then builds Core against the installed Scheduler frontend. Scheduler prepares the matching Kernels, Runner and Codecs providers. Local source and package selections support mixed-source development; CI uses tools/ci/acquire_scheduler.py for explicit published dependency acquisition. See docs/develop-apps/contribute/build-test/local-dependencies.md for details. Use ./build.sh --doc to generate documentation without runtime providers.

About

SiMa.ai Palette Neat Library

Resources

Code of conduct

Contributing

Security policy

Stars

8 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

Languages