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 zhudotexe · LLM Plugin · ★ 607
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is kani safe to install? View the security audit →
kani (カニ) kani (カニ) is a lightweight and highly hackable framework for chat-based language models with tool usage/function calling. Compared to other LM frameworks, kani is less opinionated and o
| Stars | 607 |
| Forks | 30 |
| Language | Python |
| Category | LLM Plugin |
| License | MIT |
| Quality Score | 66.6077738320729/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-27 |
| Created | 2023-07-14 |
| Platforms | python |
| Est. Tokens | ~17k |
Looking for a kani alternative? If you're comparing kani 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.
[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
🤖 Everything you need to create an LLM Agent—tools, prompts, frameworks, and models—all in one place.
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
A curated list of awesome resources, tools, and other shiny things for LLM prompt engineering.
🦙 Integrating LLMs into structured NLP pipelines
Explore other popular llm plugin tools:
kani is kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023). It is categorized as a LLM Plugin with 607 GitHub stars.
kani is primarily written in Python. It covers topics such as chatgpt, framework, function-calling.
You can find installation instructions and usage details in the kani GitHub repository at github.com/zhudotexe/kani. The project has 607 stars and 30 forks, indicating an active community.
kani is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to kani on Agent Skills Hub include bigcodebench, awesome-llm-powered-agent, DemoGPT. 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: