# EGC

> Use this tool when you need to provide persistent memory to multiple AI coding agents across sessions. EGC solves the problem of lost context and state resets by offering a local runtime with SQLite-backed storage for up to 12 agents. It takes in AI agent inputs and outputs stored state, ideal for use cases requiring continuous learning and memory retention.

Canonical page: https://skillsregistry.net/skills/fmarzochi-egc  
JSON: https://api.skillsregistry.net/v1/skills/fmarzochi-egc

## Description

Local MCP runtime that gives persistent cross-session memory to 12 AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Amp, and more). SQLite-backed state survives context resets. Install: npm install -g @egchq/egc

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-07-26

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rq74paljym)
- **Repository:** <https://github.com/Fmarzochi/EGC>

## 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": "fmarzochi-egc"
    }
  }
}
```

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