zvec

zvec is a skill for Claude Code, Codex from oyi77/1ai-skills. It costs 28 tokens per session (1,549 once invoked), scanned A, original, MIT.

A guide to using ZVec, an in-process vector database for storing embeddings and finding similar items. Embeddings are numeric representations that let software compare the meaning of text or other data.

In plain words
What is it for?
Use it to store embeddings, search agent memory for related information, and build lightweight retrieval systems.
Why use it?
It helps applications add similarity search without running a separate database server.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Part of the 1ai-skills plugin — 187 skills, 4 commands shipped together

Good fit Use it to store embeddings, search agent memory for related information, and build lightweight retrieval systems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oyi77/1ai-skills/zvec
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add oyi77/1ai-skills --skill zvec
Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code, Codex.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 187 skills, 4 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zvec

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/zvec/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/zvec)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/zvec"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/zvec/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for zvec

Your own site · 80×15
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/zvec"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/zvec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,549 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01549
Opus 5 $0.00014 $0.00775
Sonnet 5 $0.00006 $0.00310
Haiku 4.5 $0.00003 $0.00155

Measured 6d ago against content hash 70c9af62f5ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zvec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

core/zvec/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZVec Skill

Alibaba's lightweight in-process vector database - "The SQLite of Vector Databases"

Overview

ZVec is an open-source, in-process vector database from Alibaba's Tongyi Lab. It's lightweight, blazing fast, and embeds directly into your application - no server needed. Built on Proxima (Alibaba's battle-tested vector search engine used in production across Taobao, Ele.me, and more).

Anti-Rationalization Table

Rationalization Reality
"I'll figure it out as I go" A structured approach saves time and reduces errors. Follow the workflow in this skill rather than improvising.
"I already know this topic" Familiarity breeds shortcuts. Use the checklist to verify you haven't missed critical steps.
"This doesn't apply to my situation" The patterns here generalize across contexts. Adapt, don't skip — the underlying principles hold.
"One more tool will fix it" Adding complexity rarely solves process gaps. Master the core workflow first.

When to Use

Trigger phrases:

  • "Mikolov et al."
  • "Zero-copy vector operations for efficient similarity search and embedding storag"

Use this skill when you need:

  • Lightweight vector storage with minimal setup
  • Fast local RAG without external services
  • Edge AI with on-device embeddings
  • Simple API that "just works"
  • Production-grade performance in a tiny package

Key Features

  • Automated workflow execution with error recovery
  • Configurable parameters for different use cases
  • Integration with existing tooling and pipelines
  • Detailed logging and status reporting

🚀 Blazing Fast

  • Searches billions of vectors in milliseconds
  • Built on Alibaba's Proxima engine
  • Optimized for low latency

📦 Simple, Just Works

  • pip install zvec and start searching
  • No servers, no config, no daemon
  • Runs wherever your code runs

🌍 Runs Anywhere

  • macOS (ARM64)
  • Linux (x86_64, ARM64)
  • Python 3.10-3.12
  • Node.js support

🔍 Rich Query Support

  • Dense and sparse vectors
  • Hybrid search with filters
  • Multiple index types (Flat, HNSW, IVF)

Read the full file on GitHub · 223 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 223 lines · 28 tokens per session scan A 70c9af62f5ee

Subscribe to this mod's changes

zvec is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,549 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.