# vecRecall

> vecRecall — snowfoxhq-vecrecall. Use this tool when you need to improve the long-term memory of AI agents, enabling more accurate and efficient context recall. VecRecall solves the problem of information retrieval and organization, boosting recall rates from 84% to 96.6%+. It takes in vector-based queries and outputs relevant information through a separate SQLite UI layer, ideal for applications requiring flexible and high-performance memory support.

Canonical page: https://skillsregistry.net/skills/snowfoxhq-vecrecall  
JSON: https://api.skillsregistry.net/v1/skills/snowfoxhq-vecrecall

## Description

VecRecall 是一个改进版的 AI 长期记忆系统。它基于对原版 MemPalace 的深度分析重新构建，核心设计理念是将“信息检索”与“信息组织”彻底解耦。  通过纯向量检索路径和独立的 SQLite UI 层，VecRecall 在保持灵活组织的同时，将召回率（R@5）从原版的 84% 提升至 96.6%+，为 AI Agent 提供更精准、更高效的上下文记忆支持。

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/snowfoxHQ/vecRecall)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "snowfoxhq-vecrecall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/snowfoxhq-vecrecall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/snowfoxhq-vecrecall/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt