Home / google-ai-edge / litert · GitHub

AGENTS.md@tensorA

AGENTS.md@tensor from google-ai-edge/litert is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add google-ai-edge/litert/tensor/AGENTS.md@git:20261020.9cd87cc

Pins git:20261020.9cd87cc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
google-ai-edge/litert
Path
tensor/AGENTS.md
Versions recorded
2
Latest version
git:20261020.9cd87cc, committed Oct 20, 2026
First version recorded
Oct 19, 2026
Size
6,003 bytes
Repository stars
3,513
License
Apache-2.0

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Instructions for `//tensor/`

<!-- disableFinding(LINE_OVER_80) -->

This directory contains the C++ **LiteRT Tensor API**: a lightweight, backend-agnostic graph construction and execution framework for on-device generative AI and ML models across XNNPACK (CPU), ML Drift (OpenCL/Metal/WebGPU GPU), TFLite FlatBuffer export, and multi-backend `ModelChain` runners.

## 1. Repository Layout

| Path | Purpose |
|---|---|
| `tensor.h`, `arithmetic.h`, `datatypes.h`, `buffer.h` | Core Tensor API graph primitives (`TensorHandle`, `Shape`, `Type`, `Quantization`, arithmetic ops). |
| `ops/` | Core operator definitions (`FullyConnected`, `BatchMatMul`, `DepthwiseConv2D`, `Concatenation`, `Slice`, `Reshape`, `Transpose`, `Softmax`, `Select`, etc.). |
| `examples/ops/transformer/` | Tier-1 reusable transformer building blocks (`RmsNorm`, `RoPE`, `ScaledDotProductAttention`, `GatedMlp`, etc.) templated on backend mixins. |
| `examples/utils/` | Checkpoint and config helpers (`SafetensorLoader`, `LazyTensorMapping`, `TensorLoadingHooks`, `minijson`). |
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add google-ai-edge/litert/tensor/AGENTS.md@sha256:256cf25c98363cbd

The line at the top of this page pins the label git:20261020.9cd87cc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fxnbspyuw7lzj6nj.svg)](https://markdownregistry.com/a/art_fxnbspyuw7lzj6nj)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 19, 2026 and Oct 20, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261020.9cd87cc latest2026-10-20 9cd87cc 6,003 BA view · diff
git:20261019.faa57c62026-10-19 faa57c6 5,160 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (6003 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

google-ai-edge/litert · 3,513 stars · license Apache-2.0 · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_fxnbspyuw7lzj6nj
GET https://markdownregistry.com/api/v1/resolve?ref=google-ai-edge/litert/tensor/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/256cf25c98363cbdebe4317def58893d22082e622ccf996efc8316645975aaba

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from google-ai-edge/litert

auto_quant SKILL.md skill
google-ai-edge/litert · litert_quantizer/litert_quantizer/experimental/skills/auto_quant/SKILL.md · Systematically explore quantization configurations for a TFLite model using the LiteRT Quantizer API, finding the…
git:20260930.7278fe8 · audit A · 3,513 stars

Every file in google-ai-edge/litert

Browse by kind, by grade A, or by owner.