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 Merit-Systems · LLM Plugin · ★ 542
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is echo safe to install? View the security audit →
Echo User-pays AI infrastructure. Drop in Echo, users pay for their own usage—you never front costs. Skip the hard choice between fronting API costs, high-friction BYOK flows, or building billing from scratch. Read the docs Read our announcement The Problem Building AI apps forces you to pick your poison:
| Stars | 542 |
| Forks | 89 |
| Language | TypeScript |
| Category | LLM Plugin |
| Quality Score | 62.8148466483837/100 |
| Open Issues | 106 |
| Last Updated | 2026-06-26 |
| Created | 2025-05-05 |
| Platforms | gemini, node |
| Est. Tokens | ~15k |
Looking for a echo alternative? If you're comparing echo 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.
Giselle: AI App Builder. Open Source.
Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, fai
Multi-Model Chat — Compare responses from multiple AI models side by side in real-time. Supports GPT, Claude,
Search + Chat = SearChat(AI Chat with Search), Support OpenAI/Anthropic/VertexAI/Gemini, DeepResearch, SearXNG
Debug your AI agents
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
Explore other popular llm plugin tools:
echo is The User Pays AI SDK. It is categorized as a LLM Plugin with 542 GitHub stars.
echo is primarily written in TypeScript. It covers topics such as anthropic, billing, gemini.
You can find installation instructions and usage details in the echo GitHub repository at github.com/Merit-Systems/echo. The project has 542 stars and 89 forks, indicating an active community.
The top alternatives to echo on Agent Skills Hub include giselle, inferock-bench, multi-model-chat. 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: