# codex-agent-mem

> codex-agent-mem — marcelocaporale-codex-agent-mem. Use this tool when you need to efficiently manage local memory for AI agent workflows, solving issues of data storage and retrieval for models like Codex, Claude, and Gemini. It provides a compact and read-only memory layer with SQLite and FTS5 support, eliminating the need for an external memory server. Ideal for use cases requiring local-first model context protocol and token savings, such as git-based workflows.

Canonical page: https://skillsregistry.net/skills/marcelocaporale-codex-agent-mem  
JSON: https://api.skillsregistry.net/v1/skills/marcelocaporale-codex-agent-mem

## Description

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## 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/MarceloCaporale/codex-agent-mem)

## 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": "marcelocaporale-codex-agent-mem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/marcelocaporale-codex-agent-mem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/marcelocaporale-codex-agent-mem/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