{"id":26792121,"url":"https://github.com/gizatechxyz/luminair","last_synced_at":"2025-06-26T12:05:35.159Z","repository":{"id":263563442,"uuid":"864909228","full_name":"gizatechxyz/LuminAIR","owner":"gizatechxyz","description":"A zkML framework for ensuring the integrity of computational graphs using Circle STARK proofs","archived":false,"fork":false,"pushed_at":"2025-06-23T07:26:05.000Z","size":11343,"stargazers_count":41,"open_issues_count":8,"forks_count":22,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-06-23T08:29:14.528Z","etag":null,"topics":["ai","deep-learning","stark","zero-knowledge","zk"],"latest_commit_sha":null,"homepage":"https://luminair.gizatech.xyz","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gizatechxyz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-09-29T13:48:33.000Z","updated_at":"2025-06-23T07:20:06.000Z","dependencies_parsed_at":"2024-11-19T08:36:24.213Z","dependency_job_id":"8724294e-cc4d-4476-a0f8-c8019036e992","html_url":"https://github.com/gizatechxyz/LuminAIR","commit_stats":null,"previous_names":["raphaeldkhn/luminair","gizatechxyz/luminair"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gizatechxyz/LuminAIR","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gizatechxyz%2FLuminAIR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gizatechxyz%2FLuminAIR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gizatechxyz%2FLuminAIR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gizatechxyz%2FLuminAIR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gizatechxyz","download_url":"https://codeload.github.com/gizatechxyz/LuminAIR/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gizatechxyz%2FLuminAIR/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261631997,"owners_count":23187264,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","deep-learning","stark","zero-knowledge","zk"],"created_at":"2025-03-29T15:20:07.499Z","updated_at":"2025-06-26T12:05:35.142Z","avatar_url":"https://github.com/gizatechxyz.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LuminAIR\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"docs/images/gh-banner.png\" style=\"width: 70%; height: auto;\"\u003e\n  \u003c/br\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ch3\u003e\n    \u003ca href=\"https://luminair.gizatech.xyz/welcome\"\u003e\n      Documentation\n    \u003c/a\u003e\n    \u003cspan\u003e | \u003c/span\u003e\n    \u003ca href=\"https://luminair.gizatech.xyz/more/roadmap\"\u003e\n      Roadmap\n    \u003c/a\u003e\n    \u003cspan\u003e | \u003c/span\u003e\n    \u003ca href=\"https://luminair.gizatech.xyz/more/benchmarks\"\u003e\n      Benchmarks\n    \u003c/a\u003e\n  \u003c/h3\u003e\n  \u003c/br\u003e\n\u003c/div\u003e\n\nLuminAIR is a **Machine Learning** framework that leverages [Circle STARK Proofs](https://eprint.iacr.org/2024/278) to ensure the integrity of computational graphs.\n\nIt allows provers to cryptographically demonstrate that a computational graph has been executed correctly,\nwhile verifiers can validate these proofs with significantly fewer resources than re-executing the graph.\n\nThis makes it ideal for applications where trustlessness and integrity are paramount, such as healthcare, finance, decentralized protocols and verifiable agents.\n\n\u003e **⚠️ Disclaimer:** LuminAIR is currently under active development 🏗️.\n\n## 🚀 Quick Start\n\nTo see LuminAIR in action, run the provided example:\n\n```bash\n$ cd examples/simple\n$ cargo run\n```\n\n```rust\nuse luminair_graph::{graph::LuminairGraph, StwoCompiler};\nuse luminal::prelude::*;\n\nfn main() -\u003e Result\u003c(), Box\u003cdyn std::error::Error\u003e\u003e {\n    let mut cx = Graph::new();\n\n    // Define tensors\n    let a = cx.tensor((2, 2)).set(vec![1.0, 2.0, 3.0, 4.0]);\n    let b = cx.tensor((2, 2)).set(vec![10.0, 20.0, 30.0, 40.0]);\n    let w = cx.tensor((2, 2)).set(vec![-1.0, -1.0, -1.0, -1.0]);\n\n    // Build computation graph\n    let c = a * b;\n    let mut d = (c + w).retrieve();\n\n    // Compile the computation graph\n    cx.compile(\u003c(GenericCompiler, StwoCompiler)\u003e::default(), \u0026mut d);\n\n    // Execute and generate a trace of the computation graph\n    let trace = cx.gen_trace()?;\n\n    // Generate proof and verify\n    let proof = cx.prove(trace)?;\n    cx.verify(proof)?;\n\n    Ok(())\n}\n```\n\n## 📖 Documentation\n\nYou can check our official documentation [here](https://luminair.gizatech.xyz/).\n\n## 🔮 Roadmap\n\nYou can check our roadmap to unlock ML integrity [here](https://luminair.gizatech.xyz/more/roadmap).\n\n## 🫶 Contribute\n\nContribute to LuminAIR and be rewarded via [OnlyDust](https://app.onlydust.com/projects/giza/overview).\n\nCheck the contribution guideline [here](https://luminair.gizatech.xyz/more/contribute)\n\n## 📊 Benchmarks\n\nCheck performance benchmarks for LuminAIR operators [here](https://luminair.gizatech.xyz/more/benchmarks).\n\n## 💖 Contributors\n\n\u003c!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section --\u003e\n\u003c!-- prettier-ignore-start --\u003e\n\u003c!-- markdownlint-disable --\u003e\n\u003ctable\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/raphaelDkhn\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/113879115?v=4?s=100\" width=\"100px;\" alt=\"raphaelDkhn\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eraphaelDkhn\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=raphaelDkhn\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://audithub.app\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/71888134?v=4?s=100\" width=\"100px;\" alt=\"malatrax\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003emalatrax\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=zmalatrax\" title=\"Documentation\"\u003e📖\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/blewater\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/2580304?v=4?s=100\" width=\"100px;\" alt=\"Mario Karagiorgas\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eMario Karagiorgas\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=blewater\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/Tbelleng\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/117627242?v=4?s=100\" width=\"100px;\" alt=\"Tbelleng\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eTbelleng\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=Tbelleng\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/sukrucildirr\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/32969880?v=4?s=100\" width=\"100px;\" alt=\"sukrucildirr\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003esukrucildirr\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=sukrucildirr\" title=\"Documentation\"\u003e📖\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/hakymulla\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/25408889?v=4?s=100\" width=\"100px;\" alt=\"Kazeem Hakeem\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eKazeem Hakeem\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=hakymulla\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/guha-rahul\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/52607971?v=4?s=100\" width=\"100px;\" alt=\"guha-rahul\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eguha-rahul\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=guha-rahul\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd align=\"center\" valign=\"top\" width=\"14.28%\"\u003e\u003ca href=\"https://github.com/bruhhgnik\"\u003e\u003cimg src=\"https://avatars.githubusercontent.com/u/146652064?v=4?s=100\" width=\"100px;\" alt=\"Agnik\"/\u003e\u003cbr /\u003e\u003csub\u003e\u003cb\u003eAgnik\u003c/b\u003e\u003c/sub\u003e\u003c/a\u003e\u003cbr /\u003e\u003ca href=\"https://github.com/gizatechxyz/LuminAIR/commits?author=bruhhgnik\" title=\"Code\"\u003e💻\u003c/a\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\n\u003c!-- markdownlint-restore --\u003e\n\u003c!-- prettier-ignore-end --\u003e\n\n\u003c!-- ALL-CONTRIBUTORS-LIST:END --\u003e\n\n## Acknowledgements\n\nA special thanks to the developers and maintainers of the foundational projects that make LuminAIR possible:\n\n- [Luminal](https://github.com/jafioti/luminal): For providing a robust and flexible deep-learning library that serves as the backbone of LuminAIR.\n- [Stwo](https://github.com/starkware-libs/stwo): For offering a powerful prover and constraint library.\n- [Brainfuck-Stwo](https://github.com/kkrt-labs/stwo-brainfuck): Inspiration for creating AIR with the Stwo library.\n\n## License\n\nLuminAIR is open-source software released under the [MIT](https://opensource.org/license/mit) License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgizatechxyz%2Fluminair","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgizatechxyz%2Fluminair","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgizatechxyz%2Fluminair/lists"}