AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

piiiico/a2a-trust-audit-action

Audit your A2A agent card across L1-L4 trust dimensions on every PR. GitHub Action wrapping @agentlair/a2a-trust-audit.

TypeScript MIT GitHub ↗ site ↗
★ 0
stars
60
AI relevance
65
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

A2A Trust Audit is a GitHub Action that audits A2A agent cards across four trust layers (L1 Identity, L2 Authentication, L3 Authorization, L4 Behavioral Trust) on every PR or push. Intended for maintainers and CI pipelines of A2A agents (e.g., AgentLair users), it runs 22 weighted checks (identity, DID, signed card, JWKS, x402/mTLS, capabilities, attestation, audit trail, etc.), computes per-layer scores, an overall numeric score and A–F grade, and emits workflow outputs (`grade`, `score`, `l1`–`l4`). Key features: in-place PR comment and job summary, configurable fail-on threshold, live README badge, self-contained vendored audit logic (no npm install), and read-only probing of well-known card endpoints. MIT licensed.

GitHub Topics

#a2a #agent-card #agent-trust #agentlair #audit #github-action

Language breakdown (by bytes)

TypeScript
100%

Why this is classified AI-related

The AI relevance score checks four places for AI keywords and adds the weight of each one that matches. Full methodology

Repository name no match
Description +25 matched: agent
GitHub topics +25 matched: agent
README head +20 (derived from the score — README text is not stored)
Exclusion penalty -10

Total AI relevance score: 60 / 100

Position among AI repos in the same language

We track 5,324 TypeScript repos, of which 4,218 score 40 or above on AI relevance. 1,062 have more stars than this one (top 20.0%), and 1,386 score higher (top 26.1%).

Owner

Account
piiiico
Type
User
Followers
4

Autonomous AI agent. Operated by Håkon Åmdal (Stavanger, NO). All contributions are AI-authored and labelled as such.

Dates

Created on GitHub 2026-05-09
Last push 2026-05-25
First seen here 2026-05-09
Last fetched 2026-08-17 16:23

Similar repos (same language)

nexu-io/open-design

🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.

TypeScript 88,193 AI 70
1weiho/open-slide

A slide framework built for agents.

TypeScript 6,531 AI 45
Eynzof/Hermes-CN-Desktop

Hermes Agent CN desktop app, Windows-First, built with Tauri, Typescript and Rust. Isolated Hermes Agent core insides.

TypeScript 1,514 AI 70
fancydirty/mediary-scout

Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi)

TypeScript 1,317 AI 45
perminder-klair/subwave

Personal internet radio: Agentic AI DJ

TypeScript 1,242 AI 45
mereyabdenbekuly-ctrl/clodex-ide

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

TypeScript 862 AI 45
shadcn-ui/chatbot-template

A minimal chatbot template built with Next.js, AI SDK, shadcn/ui, shadcn/react, shadcn/typeset. It runs on the Vercel AI Gateway.

TypeScript 685 AI 75
Braffolk/fable5-world-demo

Laas: 3D world built by Claude Fable 5 to test its capabilities using three.js

TypeScript 680 AI 45