truss
A seamless bridge from model development to model delivery
Decision gist · record as of 2026-08-14
Yes. Truss is actively maintained, has no known vulnerabilities, and low install friction. It's worth installing if you need to deploy ML models to production and want to skip Docker/Kubernetes boilerplate. Best suited for teams using Baseten or those comfortable with containerized deployments; verify first whether your target infrastructure is supported.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Baseten account and API key for deployment, or compatible infrastructure.
- Models are deployed via containerization, not run locally by default.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions, making it suitable for production deployments without licensing concerns.
last release 2026-08-03 (11 days) · last repo commit 2026-08-13 · 1,188 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,327,555 downloads/mo, #4,052 on PyPI
Alternatives
Verify before relying
pip install truss
truss init my-model
cd my-model
# Edit config.yaml with model and hardware specs
truss push # Deploy to Baseten or your infrastructure- Whether Truss can deploy models to infrastructure other than Baseten without additional configuration
- Performance overhead of the Truss serving layer compared to direct framework deployment
- Supported model frameworks beyond those mentioned (vLLM, SGLang, TensorRT-LLM, transformers, diffusers, PyTorch, TensorFlow)
What it is and what it does
Truss is a deployment-focused CLI that bridges the gap between local model development and production serving. It wraps your model code, weights, and dependencies into a containerized service that behaves consistently across development and production environments. The tool abstracts away Docker, Kubernetes, and infrastructure configuration—you write a YAML config specifying the model source, hardware (GPU type), and serving engine, then push to deploy.
The package integrates with Baseten's inference stack and supports multiple serving frameworks including vLLM, SGLang, TensorRT-LLM, transformers, diffusers, PyTorch, and TensorFlow. It handles GPU allocation, secrets management, caching, and autoscaling when deployed to Baseten or compatible infrastructure. The live-reload feature lets you iterate on config changes without full rebuilds, and deployed models expose OpenAI-compatible REST APIs by default.
Use it for
- Deploy a Hugging Face transformer model to a production API endpoint with GPU acceleration and automatic scaling
- Package a custom PyTorch or TensorFlow model with preprocessing logic and serve it via an OpenAI-compatible interface
- Iterate rapidly on model serving config (quantization, sequence length, hardware) with live reload during development
- Manage model dependencies and weights in a single reproducible package that works identically in dev and production
- Optimize inference performance using TensorRT-LLM compilation for large language models without manual container setup
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Truss is actively maintained, has no known vulnerabilities, and low install friction. It's worth installing if you need to deploy ML models to production and want to skip Docker/Kubernetes boilerplate. Best suited for teams using Baseten or those comfortable with containerized deployments; verify first whether your target infrastructure is supported.
Install
truss on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance (last commit 2026-08-13) and 1188 repository stars indicate steady development. Supports Python 3.9 through 3.14.
Requires a Baseten account and API key for deployment, or compatible infrastructure. Models are deployed via containerization, not run locally by default.
License in practice
MIT license permits commercial and private use with minimal restrictions, making it suitable for production deployments without licensing concerns.
Quickstart
pip install truss
truss init my-model
cd my-model
# Edit config.yaml with model and hardware specs
truss push # Deploy to Baseten or your infrastructureVerify before relying
- Whether Truss can deploy models to infrastructure other than Baseten without additional configuration
- Performance overhead of the Truss serving layer compared to direct framework deployment
- Supported model frameworks beyond those mentioned (vLLM, SGLang, TensorRT-LLM, transformers, diffusers, PyTorch, TensorFlow)
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release <3.15,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 28 packagesaiofilesblake3boto3clickgoogle-cloud-storagehttpx-wshttpxhuggingface-hubinquirerpyjinja2keyringlibcstlogurupackagingpathspecpsutilpydanticpython-json-loggerpython-on-whalespyyamlrequestsrich-clickrichrufftenacitytomlkittruss-transferwatchfiles |
| Maintenance | Actively maintained 11 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,327,555 / month, #4,052 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: truss-0.18.25-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 › “ML model deployment CLI”
- trussTruss is a CLI tool for packaging ML models with their serving logic…
- teradatamodelopsTeradata ModelOps Client provides a CLI and SDK for managing machine…
- cogCog packages machine learning models into production-ready Docker…
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 sagemaker-serve · tensorflow-serving-api · bentoml · truss-transfer · jina · outerbounds · tecton · sglang · sagemaker-inference · cog