XNNPACK
AGENTS.md2.5k starsChanged 10 days agoLicence not identifiedView on GitHub
Guidelines for automated agents and developers contributing to XNNPACK. XNNPACK is a highly optimized library of neural network inference operators for ARM, x86, RISC-V, and WebAssembly architectures. The codebase is…
We split this AGENTS.md into the rules it gives an agent
14 rules. About 0 are common, 3 are distinctive, and 11 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Trending
More talk lately.about the whole repository
Who's talking about google/XNNPACK
- NixOS/nixpkgs“python3Packages.torch: drop submodules in favor of Nixpkgs”GitHub · Jun 23, 2023 · 13 reactions
- tensorflow/tensorflow“TF 2.11.0/2.12 fails to build in MacOS 13 - XCode 14.1 - issue with ld linker”GitHub · Oct 29, 2022 · 5 reactions
- google-ai-edge/mediapipe“Cannot build hand_tracking_gpu model with mediapipe docker : fatal error: EGL/egl.h: No such file or directory”GitHub · Jun 25, 2020 · 5 reactions
- tensorflow/tensorflow“TF 2.13.0-rc0 fails to compile on Ubuntu 22.04”GitHub · May 12, 2023 · 2 reactions
- tensorflow/tensorflow“Building TensorFlow Lite - macos_arm64 support using cmake”GitHub · Feb 26, 2021 · 2 reactions
The biggest 5 of 51 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 51
Talked about on GitHub and Hacker News (51 times).
On GitHub · 50
- Jun 23, 2023python3Packages.torch: drop submodules in favor of Nixpkgs — NixOS/nixpkgs13 reactions · 4 comments
- Oct 29, 2022TF 2.11.0/2.12 fails to build in MacOS 13 - XCode 14.1 - issue with ld linker — tensorflow/tensorflow5 reactions · 36 comments
- Jun 25, 2020Cannot build hand_tracking_gpu model with mediapipe docker : fatal error: EGL/egl.h: No such file or directory — google-ai-edge/mediapipe5 reactions · 10 comments
- May 12, 2023TF 2.13.0-rc0 fails to compile on Ubuntu 22.04 — tensorflow/tensorflow2 reactions · 38 comments
- Feb 26, 2021Building TensorFlow Lite - macos_arm64 support using cmake — tensorflow/tensorflow2 reactions · 13 comments
45 more on GitHub
- Nov 13, 2020java.io.IOException: thread interrupted when building — bazelbuild/bazel2 reactions · 4 comments
- Nov 10, 2020[onert] Introduce xnnpack backend — Samsung/ONE2 reactions · 6 comments
- Jul 12, 2026[CPU] jax.jit returns wrong results for vmapped matrix-vector product followed by reduction — jax-ml/jax1 reaction · 4 comments
- Nov 15, 2025[pthreadpool] Upstream alignment: switch to google/pthreadpool? — microsoft/vcpkg1 reaction · 4 comments
- Jan 22, 2025[Build] WASM build of `v1.20.1` with `--use_xnnpack` fails — microsoft/onnxruntime1 reaction · 11 comments
- Apr 8, 2024Performance issue in matmul when changing tile_size to fully utilize vector registers. — iree-org/iree1 reaction · 8 comments
- Jun 19, 2023Broken build due to LLVM — tensorflow/tensorflow1 reaction · 5 comments
- Mar 13, 2023armeabi-v7a assembler error — tensorflow/tensorflow1 reaction · 26 comments
- Feb 10, 2023Convolution2DTransposeBias support — VeriSilicon/tflite-vx-delegate1 reaction
- Aug 16, 2022Bazel - Download from ... returned 404 Not Found — tensorflow/tensorflow1 reaction · 6 comments
- Mar 9, 2022Build fails 2.8.0-1 — rocm-arch/tensorflow-rocm1 reaction · 5 comments
- Jul 9, 2021Package XNNPACK for Tizen — nnstreamer/nnstreamer1 reaction · 2 comments
- Oct 28, 2026[XLA:CPU] Uses a pool allocator for YNN fusion ops, reducing page faults — openxla/xla0 reactions
- Oct 26, 2026Bump com.google.ai.edge.litertlm:litertlm-android from 0.14.0 to 0.18.1 — chartmann1590/ScamRadar0 reactions
- Oct 26, 2026deps(deps): bump com.google.ai.edge.litertlm:litertlm-android from 0.11.0 to 0.18.1 — secure-workflows/koog0 reactions · 1 comment
- Oct 25, 2026build(deps-dev): bump litert-lm from 0.14.0 to 0.18.1 — sycomix/LiteRT-Studio0 reactions
- Oct 24, 2026[xnnpack] fix Windows benchmark linking — luncliff/vcpkg-registrysays it tested it0 reactions
- Oct 23, 2026Bump com.google.ai.edge.litertlm:litertlm-android from 0.10.0 to 0.18.1 in /Android/src — jegly/Box0 reactions · 1 comment
- Oct 20, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Oct 7, 2026`jnp.max`/`jnp.min` do not propagate NaN on CPU when reducing 4096 or more elements — jax-ml/jax0 reactions · 5 comments
- Oct 7, 2026Add OpenHarmony platform support — google-ai-edge/LiteRT0 reactions · 1 comment
- Oct 5, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 23, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 18, 2026Patch XNNPACK broadcast partial reductions — openxla/xla0 reactions · 1 comment
- Sep 18, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 18, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 13, 2026build(deps): bump com.google.ai.edge.litertlm:litertlm-android from 0.14.0 to 0.17.0 in /android/reference-app — sycomix/LiteRT-Studio0 reactions
- Sep 11, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 10, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 9, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 7, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 5, 2026Optimize highway Exp using floating-point rounding (round_small technique). — google/highway0 reactions
- Sep 4, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 4, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 3, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 3, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Sep 2, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Aug 31, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Aug 26, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Aug 26, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Aug 26, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Aug 26, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Jul 15, 2026Add OHOS (OpenHarmony) to ARM Linux platform detection — pytorch/cpuinfo0 reactions · 3 comments
- Jul 6, 2026Copybara import of the project: — google-ai-edge/LiteRT0 reactions
- Jul 6, 2026Add a new environment option tag, kLiteRtEnvOptionTagContext, to the LiteRT C API — google-ai-edge/LiteRT0 reactions
On Hacker News · 1
- Dec 25, 2023Xnnpack: High-efficiency floating-point neural network inference operators1 point
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

