Microsoft's ONNX Runtime has disappeared from GitHub

(github.com)

325 points | by nvader 11 hours ago ago

71 comments

  • roseway4 5 hours ago

    Microsoft Agent Framework has been compromised[0]. The repo is also offline[1]. Possibly related?

    [0] https://socket.dev/blog/agent-framework-pypi-package-comprom...

    [1] https://github.com/microsoft/agent-framework

    • magnio 4 hours ago

      Without any official communications, Occam's razor means we can assume at least one admin account in Microsoft GitHub org got compromised.

      • hnlmorg 16 minutes ago

        That assumption means Occam’s Razor doesn’t apply.

        If you were looking for fewer assumptions then the conclusion would just be that an exploit got missed during the PR step.

      • brookst 2 hours ago

        Or a contributor to both of these related repos?

    • CodeCompost an hour ago

      Why are you assuming a compromise? Microsoft Ignite is happening and they announced a bunch of stuff. They're probably consolidating repos.

  • eddythompson80 9 hours ago

    FYI - ONNX will automatically exfiltrate data about your application with no way to opt out other than building it from source with telemetry disabled. Maybe you could block DNS too.

    • henryteeare 6 hours ago

      onnxruntime.disable_telemetry_events() works doesn't it?

      • mscdex 6 hours ago

        Same with setting `ORT_DISABLE_TELEMETRY=1` in the environment before loading the library.

        • nullpoint420 5 hours ago

          Not to be that guy but I don't think this is the gotcha y'all think it is. I didn't know that ONNX had telemetry.

          edit: I seem to have misunderstood the intent of the parent comments. Apologies

          • ameliaquining 5 hours ago

            Top-level comment said "no way to opt out other than building it from source with telemetry disabled", so if that's not true then this is important to know. See https://www.astralcodexten.com/p/if-its-worth-your-time-to-l...

          • mscdex 5 hours ago

            I'm just passing information for anyone who wants to disable it without recompiling anything.

          • refulgentis 4 hours ago

            I don’t understand what you mean. I’ve maintained a decently popular ONNX wrapper for years, had 0 idea there was telemetry, and this is quite useful info to have, particularly because it would be a PITA to rebuild binaries right now.

    • numpad0 8 hours ago

      Isn't ONNX itself not MS specific?

      • tadfisher 8 hours ago

        They probably mean "ONNX Runtime", which has unfortunately become synonymous with ONNX-the-standard.

    • plagiarist 8 hours ago

      Yikes. Another bad actor who thinks they are entitled to data.

      • tclancy 5 hours ago

        Much like ham radio.

        • ctrlkctrls 3 hours ago

          I don't see the connection you're implying? What has ham radio got to do with any of this? There's nothing secret or being exfil'd in ham radio since it's all unencrypted and transmitted on public airwaves. In the USA anyway. I'm not sure what other licensing authorities in other countries allow.

  • hiddenvulkcan 9 hours ago

    Maybe related to one of their packages that was compromised? Not sure if GitHub was the attack vector, but possibly tidying stuff up

    Source: https://opensourcemalware.com/blog/agent-framework-pypi-comp...

  • spdustin 10 hours ago

    I wonder if they found new vectors that backdoor'ed models could exploit, like that discussed in the most recent Phrack [^0]

    [0]: https://phrack.org/issues/73/backdoor-attacks-against-machin...

    • momojo 9 hours ago

      > The ONNX Runtime (ORT) is the most widely used engine for serving deep learning models in production. It is common for people to download ONNX models from public repositories, such as Hugging Face, and to serve them to their customers without too much scrutiny. In March 2026, we noticed a parser flaw: an ONNX model can cause ORT to read from arbitrary file paths (or memory addresses) without validations.

  • nvader 11 hours ago

    We found out about this this morning, when evals started failing in our pipelines. I've been looking around, but it doesn't seem like there was any advance warning about this.

    Does anyone know why or how a repository with 22k stars just went dark?

    • FesterCluck 11 hours ago

      Probably being used in supply chains, and got attacked.

      • robjam 10 hours ago

        That would be my guess also. About 6 months ago the azure-functions-host repo disappeared for a while (I got a concerning automated email from GitHub from my forked repo citing a ToS violation).

      • quietbritishjim 9 hours ago

        If I understand your implication, that's not what "supply chain attack" normally means. That term means attacking the mechanism that delivers your packages to deliver a different, more compromised, package. If the package itself is already compromised then that's just a straightforward dependency vulnerability.

    • Neywiny 10 hours ago

      Why do you think star amount has anything to do with ability to go dark?

      • tclancy 5 hours ago

        From a pure lumens perspective it seems obvious.

    • binsquare 10 hours ago

      it's called "Open Neural Network Exchange (ONNX)", perhaps microsoft is taking a page from OpenAI on what open meanings.

      • giancarlostoro 9 hours ago

        Considering Microsoft co-developed ONNX with Facebook... I think that the more likely scenario is they took it dark after learning that it has security issues, but they should really have left a message or something, this is amateur hour tier. GitHub repos should let you leave a "Sorry we've hidden our repo, we learned about security issues" which kind of doesn't help anyone either... since now they have to find help elsewhere, and fall victim to sketchy 'forks' from other people...

  • dangoodmanUT 9 hours ago

    This is why we vendor everything.

    You never know when it's going to vanish

    • rtpg 8 hours ago

      I do wish I could pay some money for a package manager intermediary that "magically" handles things (for example defaulting to not promoting things until 2 weeks have passed), has better perf, and generally just does the right things.

      Of course I wouldn't pay _that_ much money for it.

      • pjmlp 4 hours ago

        I don't get it, this is exactly how I have been mostly working since around 2010.

        Nothing that lands on CI/CD pipelines is able to download anything directly from Internet, rather internal repos based on Nexus, Artfactory and similar.

        Additionally everything that gets uploaded into them needs to have an approval process for the most part.

        So, not only already exists, it is an intermediate process, and you can even pay depending on the features.

      • rwiggins 8 hours ago

        Doesn't Artifactory provide exactly that? Along with having a bunch of features that are generally the right things.

        Though I'm pretty sure their enterprise pricing is "give us a call." Maybe your last sentence was a nod to this.

      • malikolivier 2 hours ago

        Such solutions exist. Some people are building it on their own. Some people just commit all their dependencies in their repository.

        If you want it enforced for a whole team, with caching on top, that's where registry proxies come in (Artifactory, Nexus, and similar). The big ones take real effort to set up, while lighter ones may be all you need.

        Vendoring your dependencies into the repo is the low-tech option that survives an upstream repo vanishing.

        Disclosure: I work at a company which sells such solutions.

      • binocularis 2 hours ago

        I’ve been using StableBuild for this sort of thing. It’s not exactly what you’re describing, but might be relevant.

        You basically point your builds at it instead of the upstream repos. Once you’ve pulled something, it keeps that version around, even if it gets deleted or changed upstream.

        Not sure if that covers what you need, but it’s worked well for me.

      • esafak 7 hours ago

        I have not tried it myself: https://github.com/artifact-keeper

    • KirinDave 9 hours ago

      If it were me, I would take the hint and maybe not trust a vendored version right now?

      • cjbgkagh 9 hours ago

        I believe vendoring in this context means forking it and serving it from your own repo.

        • katbyte 7 hours ago

          No that’s forking, vendoring usually means keeping a local copy of a library in /vendor that is automatically committed - rust and golang have first class support for this

        • kenferry 6 hours ago

          But if we think they took it down because of security issues…

  • Heliodex 10 hours ago

    The closest/furthest ahead fork I could find is https://github.com/intel/onnxruntime for anyone else needing it, though that's with Intel's OpenVINO modifications

  • Gluber 5 hours ago

    It seemed to have stalled in investment before i think. Performance especially for CPU only models ( there are some use cases for this ) seemed to have lagged a lot, behind what properly hand optimized code could do.

    The gpu work was mostly handed of e.g to TensorRT and that also seems since the push for more general LLM models have not really improved.

  • gabriela_c 6 hours ago

    As a former (tiny patch, pre-AI) contributor, didn't they have a license that requires everybody's approval to do this?

    • Arainach 6 hours ago

      No. Even if a license required all contributors to agree to change the license, there's no requirement to keep it available on Github.

  • UncleOxidant 9 hours ago

    Aren't there other ONNX runtimes out there? A quick google search shows a few written in Rust: Tract, RTen, WONNX, Burn&Candle. Also, IIRC there's a Julia-based one as well.

    • robertknight 39 minutes ago

      I maintain RTen (https://github.com/robertknight/rten). It is a good drop-in replacement for ONNX Runtime for many use cases where you are running inference on CPU (there is no GPU support yet). There is no Python or NodeJS API at present, though you could get an agent to build a small wrapper quite easily.

      • robjam 29 minutes ago

        I've used your library ocr to read serial numbers on an IoT device on a mobile phone. It was really responsive and faster than tesseractjs in a web worker. Just wanted to say thanks for such well thought software!

    • antimora 9 hours ago

      https://github.com/tracel-ai/burn-onnx

      I maintain this project at the moment.

      It convert ONNX models into native, backend-agnostic Burn code for inference and fine-tuning.

      • citizenpaul 2 hours ago

        This looks awesome, i may be using this in prod very soon. Ive had some ONNX issues this looks to solve

      • ytxm 9 hours ago

        Have used it with wasm and it's lovely, but I was kindof disappointed to learn internally it's basically another serialisation format. I imagined gigabytes of generated Rust code hehe

        • antimora 8 hours ago

          The graph is converted into Rust code that calls Burn APIs but the weights are converted into Burn's format, called burnpack (similar to safetensors but instead of JSON we use CBOR for weights meta data).

  • these 8 hours ago

    Not to take away from the fact that I don't like that this was done, but in my experience development on ONNX has been pretty slow recently. I moved away from a few months back because I felt bug fixes were coming in pretty slow, despite being reported.

    • SknCode 2 hours ago

      What do you use instead?

  • tokyovigilante 9 hours ago
  • Axodouble 10 hours ago

    Maybe related to the recent release of MAI? Or the Microsoft AI models?

  • hluska 6 hours ago

    agent-framework is down as well:

    https://github.com/microsoft/agent-framework/

  • craigacp 8 hours ago

    How odd. https://onnxruntime.ai is still up, and the packages still appear to be on PyPI, Maven Central etc. Guess I won't submit the PR I was working on tonight then.

  • sph 3 hours ago

    Microsoft, please, I can’t have popcorn every day.

  • proc0 9 hours ago

    omg, I just built something depending on this. Hopefully the web version is still cached in NPM.

  • matt3210 10 hours ago

    Someone with a copy should soft fork it

  • anon291 4 hours ago

    Better delete all the open source matrix multipliers because we're making it illegal

  • tomrod 10 hours ago

    Very concerning!

  • mrguyorama 8 hours ago

    The Maven package is still available, and the most recent version is from a few days ago:

    https://mvnrepository.com/artifact/com.microsoft.onnxruntime...

  • logicchains 5 hours ago

    Now Jensen's gone they can start dismantling the infrastructure that allows people to run models on their own hardware.

  • tekacs 9 hours ago

    So... all of these also vanished.

       microsoft/
         ├─> onnxruntime-genai                  — generative AI runtime
         ├─> onnxruntime-extensions             — custom operators
         ├─> onnxruntime-inference-examples     — inference samples
         ├─> onnxruntime-training-examples      — training samples
         ├─> onnxruntime-swift-package-manager  — Swift package distribution
         └─> onnxruntime-web-benchmark          — browser benchmark tool
    
    (possible they were gone earlier, but e.g. onnxruntime-extensions had a push yesterday)
  • gtirloni 10 hours ago
    • callmekit 5 hours ago

      The onnx repo is just a spec. Microsoft's ONNX Runtime is an implementation of the spec.

    • russdill 10 hours ago

      This is not the same package.