Flagged: environment access. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Mirascope · Agent Tool · ★ 213
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is lilypad safe to install? View the security audit →
[!CAUTION] Lilypad is now deprecated after the GA release of Mirascope and Mirascope Cloud + Router. The new module supports a significantly improved OTEL compliant Python SDK for instrumentation, and Mirascope Cloud offers a backend solution for that OTEL data. If you're looking for such tooling, we recommend checking out what we've build over in . You can find the full documentation here: https://mirascope.com/docs Lilypad will remain open-source and available for use, but
| Stars | 213 |
| Forks | 17 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 63.5356712271603/100 |
| Open Issues | 31 |
| Last Updated | 2026-01-23 |
| Created | 2024-06-05 |
| Platforms | python |
| Est. Tokens | ~916k |
These tools work well together with lilypad for enhanced workflows:
Looking for a lilypad alternative? If you're comparing lilypad with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An Automated AI-Powered Prompt Optimization Framework
Ship RAG based LLM web apps in seconds.
The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for ca
Run LLM prompts from your shell
LLMs and Machine Learning done easily
Automatic LLM-based video generation using the manim library. Usage of a code-writer and code-reviewer feedbac
Explore other popular agent tool tools:
lilypad is Open-source versioning, tracing, and annotation tooling.. It is categorized as a Agent Tool with 213 GitHub stars.
lilypad is primarily written in Python. It covers topics such as anthropic, large-language-models, llm.
You can find installation instructions and usage details in the lilypad GitHub repository at github.com/Mirascope/lilypad. The project has 213 stars and 17 forks, indicating an active community.
The top alternatives to lilypad on Agent Skills Hub include Promptimizer, autollm, gateway. 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: