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 alibaba · Agent Tool · ★ 16.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is zvec safe to install? View the security audit →
English | 中文 <img src="https://trendshift.io/api/badge/repositories/20830" alt="alibaba%2Fzvec | Trendshift" style="width: 250px; height:
| Stars | 16,030 |
| Forks | 1,006 |
| Language | C++ |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 63.670024640297/100 |
| Open Issues | 65 |
| Last Updated | 2026-09-29 |
| Created | 2025-12-05 |
| Est. Tokens | ~18k |
Looking for a zvec alternative? If you're comparing zvec 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.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Vane is an AI-powered answering engine.
Memory library for building stateful agents
Your own search engine
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Explore other popular agent tool tools:
zvec is A lightweight, lightning-fast, in-process vector database. It is categorized as a Agent Tool with 16.0k GitHub stars.
zvec is primarily written in C++. It covers topics such as agent-skills, db, embedded.
You can find installation instructions and usage details in the zvec GitHub repository at github.com/alibaba/zvec. The project has 16.0k stars and 1006 forks, indicating an active community.
zvec is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to zvec on Agent Skills Hub include claude-context, Vane, honcho. 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: