by Graph-COM · Agent Tool · ★ 186
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 | 186 |
| Forks | 34 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 55/100 |
| Open Issues | 5 |
| Last Updated | 2025-01-27 |
| Created | 2024-10-29 |
| Platforms | python |
| Est. Tokens | ~13k |
SubgraphRAG, Simple Yet Effective KG-Based RAG [[Paper]](https://arxiv.org/abs/2410.20724) Table of Contents Usage Citation Frequently Asked Questions (FQA) Usage SubgraphRAG is a retrieval-and-reasoning pipeline for knowledge-graph-based retrieval-augmented generation. For the retrieval stage, see the retrieve folder. For the reasoning stage, see the reason folder.
Looking for a SubgraphRAG alternative? If you're comparing SubgraphRAG 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.
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, ma
AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG fram
✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models
User friendly CLI tool for AI tasks. Stop thinking about LLMs and prompts, start getting results!
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: