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 Tejas-TA · LLM Plugin · ★ 417
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is predikit safe to install? View the security audit →
predikit 📈 Project Traffic Detailed breakdown of downloads by version, region, and platform: Table of Contents Install 30-second example Core API Cookbook Contributing License Turn any trained scikit-learn or XGBoost model into an LLM-callable tool — auto-generated JSON schemas, typed I/O, zero boilerplate. Install 30-second example python f
| Stars | 417 |
| Forks | 135 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 67.8666333239024/100 |
| Open Issues | 30 |
| Last Updated | 2026-08-17 |
| Created | 2026-05-25 |
| Platforms | python |
| Est. Tokens | ~4k |
Looking for a predikit alternative? If you're comparing predikit 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.
A set of tools that gives agents powerful capabilities.
Agent samples built using the Strands Agents SDK.
An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c
This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite
AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while pr
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular,
Explore other popular llm plugin tools:
predikit is pypi-predikit: Turn any sklearn/XGBoost model into an LLM-callable tool. Framework-agnostic. It is categorized as a LLM Plugin with 417 GitHub stars.
predikit is primarily written in Python. It covers topics such as agents, langchain, llm.
You can find installation instructions and usage details in the predikit GitHub repository at github.com/Tejas-TA/predikit. The project has 417 stars and 135 forks, indicating an active community.
predikit is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to predikit on Agent Skills Hub include tools, samples, agent-builder. 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: