by OpenSPG · Agent Tool · ★ 9.1k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 9,085 |
| Forks | 723 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 66/100 |
| Open Issues | 173 |
| Last Updated | 2026-01-28 |
| Created | 2024-09-21 |
| Platforms | python |
| Est. Tokens | ~16k |
KAG: Knowledge Augmented Generation English | 简体中文 | 日本語版ドキュメント What is KAG? KAG is a logical reasoning and Q&A framework based on the [OpenSPG](https://github.com/OpenSPG/openspg
Looking for a KAG alternative? If you're comparing KAG 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.
Pocket Flow: Codebase to Tutorial
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview prepara
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: