adrenai
Health Warn
- License — License: Apache-2.0
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 5 GitHub stars
Code Pass
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
No AI report is available for this listing yet.
Local-first repository guidance and native configuration for AI coding agents.
AdrenAI
AdrenAI inspects a software repository and creates minimal, compatible,
token-efficient configuration for AI coding agents. Core behavior is local,
deterministic, and does not require an AI provider.
Launch site ·
CLI guide ·
Contributing ·
Security
Why AdrenAI
- Detects repository technologies and existing agent instructions.
- Recommends a small, compatible set of versioned guidance packs.
- Generates native configuration for Codex, Claude Code, Cursor, Copilot, Kiro,
Gemini, and portableAGENTS.mdworkflows. - Previews changes before writing and preserves user-authored files.
- Validates configuration, detects managed-file drift, and plans allowlisted
quality gates. - Works locally without sending repository content to an AI provider.
Install
npm install -g adrenai
adrenai onboard .
Node.js 22 or newer is required.
Running adrenai without a command starts a read-only onboarding summary for the
current directory. It does not modify files or use AI credits.
Commands
adrenai onboard [path] [--json]
adrenai inspect [path] [--json]
adrenai recommend [path] [--json]
adrenai apply [path] [--write] [--agents=codex,claude-code,cursor]
adrenai sync [path] [--write] [--agents=...]
adrenai doctor [path] [--json]
adrenai validate [path] [--json]
adrenai drift [path] [--json]
adrenai check [path] [--run] [--json]
adrenai packs [--json]
apply only creates missing files. sync safely updates files already owned by
AdrenAI, blocks user-modified or unmanaged files, and writes a deterministic
pack lockfile. check previews safe quality gates unless --run is provided.
Supported native outputs include Codex, Claude Code, GitHub Copilot, Cursor,
Kiro, Gemini, and portable AGENTS.md.
Safety Model
AdrenAI treats repository content and community packs as untrusted input. It
uses path containment, symlink checks, create-only defaults, ownership
manifests, SHA-256 drift detection, and allowlisted quality-gate execution.
Review the security model before enabling writes or
quality-gate execution in sensitive repositories.
Development
corepack pnpm install
corepack pnpm check
corepack pnpm test
corepack pnpm build
node scripts/smoke-test.mjs
corepack pnpm site:validate
See docs/ for architecture, security, pack authoring, CLI usage, and
release procedures. Product Hunt copy, demo plans, and beta-testing materials
are maintained under launch/, demos/, andbeta/.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found