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 acodercat · LLM Plugin · ★ 199
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is cave-agent safe to install? View the security audit →
CaveAgent: Transforming LLMs into Stateful Runtime Operators "From text-in-text-out to (text&object)-in-(text&object)-out" Most LLM agents operate under a text-in-text-out paradigm
| Stars | 199 |
| Forks | 16 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 62.5456891091103/100 |
| Last Updated | 2026-09-15 |
| Created | 2025-01-23 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with cave-agent for enhanced workflows:
Looking for a cave-agent alternative? If you're comparing cave-agent 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 curated list of tools, papers, and datasets for applying AI to cybersecurity tasks. This list primarily focu
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learni
A Data analysis agent powered by llm for querying database and visualizing results
A declarative way to control LLMs.
Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into
Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.
Explore other popular llm plugin tools:
cave-agent is Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns.. It is categorized as a LLM Plugin with 199 GitHub stars.
cave-agent is primarily written in Python. It covers topics such as llm, llm-agent, llm-agents.
You can find installation instructions and usage details in the cave-agent GitHub repository at github.com/acodercat/cave-agent. The project has 199 stars and 16 forks, indicating an active community.
cave-agent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to cave-agent on Agent Skills Hub include Awesome-AI-For-Security, Awesome-LLMs-ICLR-24, data-analysis-llm-agent. 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: