No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by el1ght · LLM Plugin · ★ 136
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is aulite safe to install? View the security audit →
[]() []() []() []() []() []() []() [![
| Stars | 136 |
| Forks | 0 |
| Language | TypeScript |
| Category | LLM Plugin |
| Quality Score | 48.2797010049071/100 |
| Last Updated | 2026-06-14 |
| Created | 2026-03-22 |
| Platforms | docker, node |
| Est. Tokens | ~13k |
Looking for a aulite alternative? If you're comparing aulite with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
Intelligent Cost-Optimizing Model Router for OpenClaw
Your Digital Companion. Self-hosted Telegram bot orchestrating multiple AI providers (OpenAI, Anthropic, Googl
Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premi
MCP Fusion - The framework for AI-native MCP servers.
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
Explore other popular llm plugin tools:
aulite is EU AI Act compliance proxy for AI systems. Drop-in HTTP proxy that monitors every AI interaction for regulatory risks, logs to a tamper-proof audit trail, and generates legal-grade PDF reports. 143 ru. It is categorized as a LLM Plugin with 136 GitHub stars.
aulite is primarily written in TypeScript. It covers topics such as ai-governance, anthropic, audit.
You can find installation instructions and usage details in the aulite GitHub repository at github.com/el1ght/aulite. The project has 136 stars and 0 forks, indicating an active community.
The top alternatives to aulite on Agent Skills Hub include palico-ai, ClawRoute, chibi. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: