{"data":{"slug":"pykeio-ort","name":"ort","tagline":"Fast ML inference and training for ONNX models in Rust","github_url":"https://github.com/pykeio/ort","owner":"pykeio","repo":"ort","owner_avatar_url":"https://avatars.githubusercontent.com/u/62268720?v=4","primary_language":"Rust","stars":2472,"forks":263,"topics":["ai","ai-training","fine-tuning","inference","machine-learning","onnx","onnxruntime","rust"],"archived":false,"github_pushed_at":"2026-08-23T20:46:26+00:00","maintenance_label":"Very active","stars_delta_30d":56,"url":"https://www.graphcanon.com/tools/pykeio-ort","markdown_url":"https://www.graphcanon.com/tools/pykeio-ort.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pykeio-ort","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pykeio-ort","description":"Fast ML inference & training for ONNX models in Rust","homepage_url":"https://ort.pyke.io/","license":"Apache-2.0","open_issues":2,"watchers":18,"ai_summary":"pykeio/ort offers high-performance operations for ONNX model inference and training written in Rust.","readme_excerpt":"<div align=center>\n<img src=\"https://parcel.pyke.io/v2/cdn/assetdelivery/ortrsv2/docs/trend-banner.png\" width=\"350px\">\n</div>\n<div align=center>\n<a href=\"https://app.codecov.io/gh/pykeio/ort\" target=\"_blank\"><img alt=\"Coverage Results\" src=\"https://img.shields.io/codecov/c/gh/pykeio/ort?style=for-the-badge\"></a> <img alt=\"MSRV\" src=\"https://img.shields.io/crates/msrv/ort?style=for-the-badge\"> <img alt=\"ONNX Runtime\" src=\"https://img.shields.io/badge/onnxruntime-v1.28.0-blue?style=for-the-badge&logo=cplusplus\">\n</div>\n<hr /><br />\n\n`ort` is a Rust interface for performing hardware-accelerated inference & training on machine learning models in the [Open Neural Network Exchange](https://onnx.ai/) (ONNX) format.\n\nBased on the now-inactive [`onnxruntime-rs`](https://github.com/nbigaouette/onnxruntime-rs) crate, `ort` is primarily a wrapper for Microsoft's [ONNX Runtime](https://onnxruntime.ai/) library, but offers support for [other pure-Rust runtimes](https://ort.pyke.io/backends).\n\n`ort` with ONNX Runtime is super quick - and it supports almost [any hardware accelerator](https://ort.pyke.io/perf/execution-providers) you can think of. Even still, it's light enough to run on your users' devices.\n\nWhen you need to deploy a PyTorch/TensorFlow/Keras/scikit-learn/PaddlePaddle model either on-device or in the datacenter, `ort` has you covered.\n\n## 📖 Documentation\n- [Guide](https://ort.pyke.io/)\n- [API reference](https://docs.rs/ort/2.0.0-rc.13/ort/)\n- [Examples](https://github.com/pykeio/ort/tree/main/examples)\n- [Migrating from v1.x to v2.0](https://ort.pyke.io/migrating/v2)\n\n## 🤔 Support\n- [Discord: `#🦀｜ort-general`](https://discord.gg/uQtsNu2xMa)\n- [GitHub Discussions](https://github.com/pykeio/ort/discussions)\n\n## 🌠 Backers\n<a href=\"https://opencollective.com/pyke-osai\">\n<img src=\"https://opencollective.com/pyke-osai/backers.svg\" />\n</a>\n\n## 💖 FOSS projects using `ort`\n<sub>[Open a PR](https://github.com/pykeio/ort/pulls) to add your project here 🌟</sub>\n\n\n\n- **[Text Embeddings Inference (TEI)](https://github.com/huggingface/text-embeddings-inference)** uses `ort` to deliver high-performance ONNX Runtime inference for text embedding models.\n- **[Magika](https://github.com/google/magika)** uses `ort` for neural network-based file type detection.\n- **[retto](https://github.com/NekoImageLand/retto)** uses `ort` for reliable, fast ONNX inference of PaddleOCR models on Desktop and WASM platforms.\n- **[edge-transformers](https://github.com/npc-engine/edge-transformers)** uses `ort` for accelerated transformer model inference at the edge.\n- **[`sbv2-api`](https://github.com/neodyland/sbv2-api)** is a fast implementation of Style-BERT-VITS2 text-to-speech using `ort`.\n- **[BoquilaHUB](https://github.com/boquila/boquilahub/)** uses `ort` for local AI deployment in biodiversity conservation efforts.\n- **[CamTrap Detector](https://github.com/bencevans/camtrap-detector)** uses `ort` to detect animals, humans and vehicles in trail camera imagery.\n- **[Ortex](https://github.com/relaypro-open/ortex)** uses `ort` for safe ONNX Runtime bindings in Elixir.\n- **[oar-ocr](https://github.com/GreatV/oar-ocr)** A comprehensive OCR library, built in Rust with `ort` for efficient inference.\n- **[`FastEmbed-rs`](https://github.com/Anush008/fastembed-rs)** uses `ort` for generating vector embeddings, reranking locally.\n- **[Ahnlich](https://github.com/deven96/ahnlich)** uses `ort` to power their AI proxy for semantic search applications.\n- **[Murmure](https://github.com/Kieirra/murmure)** uses `ort` as its core engine, leveraging NVIDIA Parakeet to deliver fully local, free, private and cross‑platform Speech‑to‑Text enhanced with LLM post‑processing.\n- **[Valentinus](https://github.com/kn0sys/valentinus)** uses `ort` to provide embedding model inference inside LMDB.\n- **[SilentKeys](https://github.com/gptguy/silentkeys)** uses `ort` for fast, on-device real-time dictation with NVIDIA Parakeet and Silero VAD.\n- **[Xybrid](https://github.com/xybrid-ai/xyb","github_created_at":"2022-11-26T19:26:15+00:00","created_at":"2026-07-11T11:38:09.997162+00:00","updated_at":"2026-08-24T00:01:38.526759+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"inference","name":"inference"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"onnx","name":"onnx"},{"slug":"rust","name":"rust"}],"trust":{"provenance":{"is_fork":false,"github_id":570985989,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T00:01:37.685Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":0,"last_release_at":"2026-07-28T08:13:09Z","stars_delta_30d":56,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:38:11.390Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T00:01:38.159Z"},"languages":{"value":["rust"],"source":"github.language","observed_at":"2026-08-24T00:01:38.159Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-24T00:01:38.159Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When your project involves ONNX models that require fast inference times or efficient fine-tuning","If you prefer a tool built in Rust for better performance and memory safety compared to tools using other languages"],"when_not_to_use":["When the primary development language is not compatible with Rust bindings","For projects requiring broad model support beyond ONNX, as ort specializes only in ONNX models and does not cover a wide array of formats like some competitors might"],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:29:29.038Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"ort accelerates ML inference and training tasks for ONNX models with high-performance Rust operations"}]}}