snc4onnx
Simple tool to combine onnx models. Simple Network Combine Tool for ONNX.
Decision gist · record as of 2026-08-14
Yes, if you need to merge ONNX models and prefer a CLI or simple API over writing ONNX graph code directly. Install friction is negligible, maintenance is active, and the MIT license poses no restrictions. No known vulnerabilities. Suitable for production use in model composition workflows.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires ONNX models to be valid and operator names to be correctly specified; mismatched connection points will cause merge failure.
- Low install friction with no runtime dependencies.
- Active maintenance as of February 2026, though repository shows modest engagement (17 stars).
License · maintenance · safety
MIT License (permissive) — MIT License permits commercial and private use with minimal restrictions; suitable for most projects.
last release 2025-10-08 (310 days) · last repo commit 2026-02-24 · 17 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 84,335 downloads/mo, #14,006 on PyPI
Alternatives
Verify before relying
pip install snc4onnx
from snc4onnx import combine
combined = combine(
srcop_destop=[['output', 'flow_init']],
op_prefixes_after_merging=['init', 'next'],
input_onnx_file_paths=['model1.onnx', 'model2.onnx']
)- Whether the tool handles complex multi-branch model topologies or only sequential connections.
- Performance characteristics when merging large models or many models in sequence.
- Whether intermediate validation or error recovery is available during multi-step merges.
What it is and what it does
snc4onnx is a command-line and Python API tool for merging two or more ONNX neural network models into a single combined model. It works by connecting the output operators of one model to the input operators of another, with optional prefixing of operator names to prevent naming conflicts when models share common operation names. The tool runs ONNX simplification on the merged result by default to remove redundant operations.
The package is designed for developers who want to compose pre-trained models without writing custom graph manipulation code. It supports both file-based workflows (reading and writing .onnx files) and in-memory graph objects, making it suitable for both CLI automation and programmatic integration into larger pipelines.
Use it for
- Combine encoder and decoder ONNX models into a single end-to-end inference model for deployment.
- Merge feature extraction and classification models trained separately into one unified network.
- Chain multiple specialized models (e.g., preprocessing, main inference, post-processing) into a single deployable artifact.
- Fuse stereo vision or multi-stage models where outputs of one stage feed into the next.
- Automate model composition in CI/CD pipelines without writing custom ONNX graph code.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to merge ONNX models and prefer a CLI or simple API over writing ONNX graph code directly.
Install friction is negligible, maintenance is active, and the MIT license poses no restrictions. No known vulnerabilities. Suitable for production use in model composition workflows.
Install
snc4onnx on PyPI
Before you install
Low install friction with no runtime dependencies. Active maintenance as of February 2026, though repository shows modest engagement (17 stars).
Requires ONNX models to be valid and operator names to be correctly specified; mismatched connection points will cause merge failure.
License in practice
MIT License permits commercial and private use with minimal restrictions; suitable for most projects.
Quickstart
pip install snc4onnx
from snc4onnx import combine
combined = combine(
srcop_destop=[['output', 'flow_init']],
op_prefixes_after_merging=['init', 'next'],
input_onnx_file_paths=['model1.onnx', 'model2.onnx']
)Verify before relying
- Whether the tool handles complex multi-branch model topologies or only sequential connections.
- Performance characteristics when merging large models or many models in sequence.
- Whether intermediate validation or error recovery is available during multi-step merges.
Package facts
| License | MIT License permissive |
| Python support | Supports the current Python release >=3.6 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | None |
| Maintenance | Actively maintained 310 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 84,335 / month, #14,006 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: snc4onnx-1.0.14-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “merge onnx models”
- snc4onnxMerges multiple ONNX neural network models into a single combined…
- simple-onnx-processing-toolsA collection of command-line tools for transforming ONNX models:…
- onnx2torchConverts ONNX models to PyTorch modules with a simple API, supporting…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also sng4onnx · snd4onnx · sod4onnx · sor4onnx · sne4onnx · sna4onnx · scs4onnx · soc4onnx · soa4onnx · simple-onnx-processing-tools