# loci

> loci — 3m1ry33t-loci. Use this tool when you need to manage and share knowledge across multiple projects, leveraging git capabilities to store and retrieve memories. Loci solves the problem of fragmented information and duplicated efforts by providing a centralized cross-project memory for AI agents. It accepts project data as input and outputs relevant memories to inform agent decisions, ideal for use in complex, multi-project environments.

Canonical page: https://skillsregistry.net/skills/3m1ry33t-loci  
JSON: https://api.skillsregistry.net/v1/skills/3m1ry33t-loci

## Description

cross-project memory tool for AI agents

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/3M1RY33T/loci)

## 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": "3m1ry33t-loci"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/3m1ry33t-loci` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/3m1ry33t-loci/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