by christopherkarani · MCP Server · ★ 801
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Wax safe to install? View the security audit →
Wax is a high-performance, single-file memory layer for AI agents on Apple platforms. On-device, private, and portable. No server and no cloud dependency. English · Español · Français · 日本語 · <a href="Resources/locales/R
npx -y waxmcp@latest mcp install --scope userTaken from the project's README on GitHub. Check the security audit before running it.
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 →
| Stars | 801 |
| Forks | 54 |
| Language | Swift |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 68.4897707145176/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-26 |
| Created | 2026-01-20 |
| Platforms | cli, mcp |
| Est. Tokens | ~18k |
These tools work well together with Wax for enhanced workflows:
Looking for a Wax alternative? If you're comparing Wax 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.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowl
Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools,
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP:
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microso
The control plane for AI coding agents.
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market suppo
Explore other popular mcp server tools:
Wax is Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift. It is categorized as a MCP Server with 801 GitHub stars.
Wax is primarily written in Swift. It covers topics such as ai-agents, cli, coreml.
The README on GitHub (github.com/christopherkarani/Wax) gives: npx -y waxmcp@latest mcp install --scope user. Usage details are in the same README.
Wax is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to Wax on Agent Skills Hub include mcp-memory-service, knowledge-rag, SocratiCode. 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: