AGENTS.md@packages/flutter_edge_ai_llamaA

AGENTS.md@packages/flutter_edge_ai_llama from denisovav/flutter_edge_ai is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add denisovav/flutter_edge_ai/packages/flutter_edge_ai_llama/AGENTS.md@git:20261028.1d80d2d

Pins git:20261028.1d80d2d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
denisovav/flutter_edge_ai
Path
packages/flutter_edge_ai_llama/AGENTS.md
Versions recorded
5
Latest version
git:20261028.1d80d2d, committed Oct 28, 2026
First version recorded
Oct 16, 2026
Size
2,769 bytes
Repository stars
649
License
MIT

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

# llama.cpp adapter maintenance

Version 0.0.4 adapts core 2.5.0+ through
public engine libraries and published llamadart 0.15.1. Keep source qualification
separate from hosted consumer qualification. Inference routes by declared type.
LlamaEmbeddingBackend registers self-contained GGUF through core's embedding SPI; see doc/embeddings.md.

- Minimum Flutter/Dart follows core (3.44/3.12). Connector CI pins Flutter 3.47.1
  for reproducible checks; verify.py also reads the workspace SDK from `.fvmrc`. Do not raise the whole workspace floor for this adapter.
- Run `python3 tool/verify.py contracts` and `python3 tool/verify.py package`.
  The latter validates hosted consumers without workspace resolution or overrides.
- Shipped code uses `engine.dart` and conditional `engine_web.dart`, never core src.
- Public exports are the inference provider, embedding backend and projector resolver. Tool messages use core types.
  Implementation classes and diagnostics stay internal; the loader factory is internal and test-only.
- Model/device lanes require machine-reported execution of the selected smoke.
  Optional features use `verify.py capabilities` with explicit compatible fixtures.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add denisovav/flutter_edge_ai/packages/flutter_edge_ai_llama/AGENTS.md@sha256:21f465eee6d14733

The line at the top of this page pins the label git:20261028.1d80d2d, 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_cnb5n22bqmfntvse.svg)](https://markdownregistry.com/a/art_cnb5n22bqmfntvse)

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

Versions

The registry has recorded 5 versions of this file, between Oct 16, 2026 and Oct 28, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
git:20261028.1d80d2d latest2026-10-28 1d80d2d 2,769 BA view · diff
git:20261021.cd4b2ed2026-10-21 cd4b2ed 2,769 BA view · diff
git:20261021.02009ec2026-10-21 02009ec 2,562 BA view · diff
git:20261019.fee75792026-10-19 fee7579 2,242 BA view · diff
git:20261016.52d16e72026-10-16 52d16e7 2,242 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 (2769 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

denisovav/flutter_edge_ai · 649 stars · license MIT · pushed 2026-10-31 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cnb5n22bqmfntvse
GET https://markdownregistry.com/api/v1/resolve?ref=denisovav/flutter_edge_ai/packages/flutter_edge_ai_llama/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/21f465eee6d14733700634b39e2e1eaee056611bc41b3b8a3f8cb09c699057a2

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 denisovav/flutter_edge_ai

build-native SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/build-native/SKILL.md · Rebuild native LiteRT-LM prebuilts for flutter_edge_ai (iOS / macOS / Linux / Windows / Android) — covers required…
git:20261021.5301958 · audit A · 649 stars
ci-status SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/ci-status/SKILL.md · Check CI status for current branch or PR, show failed job logs
git:20260616.784c411 · audit A · 649 stars
ddp-device-test SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/ddp-device-test/SKILL.md · Run an Android integration test on a real phone through Google's Developer Device Platform (DDP) — reserve the device…
git:20261014.a4f49fa · audit A · 649 stars
release SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/release/SKILL.md · Release flutter_edge_ai — bump versions, optionally re-publish native prebuilts (iOS/macOS/Linux/Windows/Android…
git:20261030.68195f3 · audit A · 649 stars
review-pr SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/review-pr/SKILL.md · Comprehensive PR review for flutter_edge_ai. Runs 10 specialized reviewers in parallel (4 platform-specific + 6…
git:20261027.02500de · audit A · 649 stars
upgrade-genkit SKILL.md skill
denisovav/flutter_edge_ai · .claude/skills/upgrade-genkit/SKILL.md · Realign the genkit_flutter_edge_ai / genkit_hybrid packages when flutter_edge_ai's core API changes or when `genkit`…
git:20261020.377d822 · audit A · 649 stars
AGENTS.md AGENTS.md file
denisovav/flutter_edge_ai · AGENTS.md
git:20261030.68195f3 · audit B · 649 stars
packing-list SKILL.md skill
denisovav/flutter_edge_ai · codelabs/on-device-agent-flutter-gemma/complete/assets/skills/packing-list/SKILL.md · Builds a packing list for a trip. Use when the user asks what to pack, or names a trip and its length.
git:20261012.639d5ec · audit A · 649 stars
tip-split SKILL.md skill
denisovav/flutter_edge_ai · codelabs/on-device-agent-flutter-gemma/complete/assets/skills/tip-split/SKILL.md · Splits a restaurant bill, with tip, between several people. Use when the user asks how much each person pays.
git:20261012.639d5ec · audit A · 649 stars
packing-list SKILL.md skill
denisovav/flutter_edge_ai · codelabs/on-device-agent-flutter-gemma/step_02_first_skill/assets/skills/packing-list/SKILL.md · Builds a packing list for a trip. Use when the user asks what to pack, or names a trip and its length.
git:20261012.639d5ec · audit A · 649 stars
packing-list SKILL.md skill
denisovav/flutter_edge_ai · codelabs/on-device-agent-flutter-gemma/step_03_intents/assets/skills/packing-list/SKILL.md · Builds a packing list for a trip. Use when the user asks what to pack, or names a trip and its length.
git:20261012.639d5ec · audit A · 649 stars
flutter-edge-ai-builtin-ai SKILL.md skill
denisovav/flutter_edge_ai · packages/flutter_edge_ai/skills/flutter-edge-ai-builtin-ai/SKILL.md · Use when running the device's own model with flutter_edge_ai_builtin_ai — Gemini Nano on Android or in desktop Chrome…
git:20261019.0c626b2 · audit A · 649 stars

Every file in denisovav/flutter_edge_ai

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