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 Ciao1019 · MCP Server · ★ 142
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Petrichor safe to install? View the security audit →
Petrichor 让知识被人读懂，也被 AI Agent 正确调用 开源、自托管的知识平台：用 Markdown 写作，把内容编译成语义 Wiki，\ 再通过 Agentic RAG 生成可追溯的回答。 A self-hosted knowledge platform that turns Markdown into wikis, evidence and agent-ready knowledge. 产品介绍 · 在线体验 · 快速开始 · 文档中心 · GitHub Wiki ✨ 为什么是 Petrichor 知识不是一次性向量。 原文分片、推荐问题、语义 Wiki 和文章目录并存，分别处理事实、用户问法、概念关系与结构性问题。 检索和阅读严格分离。 Agent 先用 Search / Outline 定位，再 Read 原文形成 Evidence，避免把一批相似片段无差别塞进上下文。 Wiki 是可维护的知识中间层。 从整篇文档抽取实体、概念和关系，让多篇文章聚合到同一页面，同时保留来源引用与新鲜度指纹。 知识可以交给其它 Agent。 除 REST 和 MCP 外，还能导出 OKF、Obsidian 与可安装的 Agent Skill 包。 运行边界完全可控。
| Stars | 142 |
| Forks | 13 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 64.8527272601048/100 |
| Open Issues | 12 |
| Last Updated | 2026-09-29 |
| Created | 2026-04-13 |
| Platforms | mcp, node |
| Est. Tokens | ~16k |
These tools work well together with Petrichor for enhanced workflows:
Looking for a Petrichor alternative? If you're comparing Petrichor with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Bui
Aser is a lightweight, self-assembling AI Agent frame.
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stabl
c4 GenAI Suite
Local AI-powered document search and editing with first-in-class hybrid retrieval, LLM answers, WebUI, REST AP
Explore other popular mcp server tools:
Petrichor is A self-hosted knowledge platform for humans and AI agents — publish wikis, blogs, and portable Agent Skills.. It is categorized as a MCP Server with 142 GitHub stars.
Petrichor is primarily written in TypeScript. It covers topics such as agent-skills, ai-agent, blog.
You can find installation instructions and usage details in the Petrichor GitHub repository at github.com/Ciao1019/Petrichor. The project has 142 stars and 13 forks, indicating an active community.
Petrichor is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Petrichor on Agent Skills Hub include swarmvault, aser, llm-wiki. 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: