# chatmux

> chatmux — echoedinvoker-chatmux. Use this tool when you need to unify and manage multiple chat platforms, such as LINE and Telegram, behind a single data layer. Chatmux solves the problem of fragmented chat data by storing messages in JSONL and SQLite/FTS5 formats, and provides six MCP tools accessible via streamable HTTP on localhost. It is ideal for users seeking a self-hosted, local-first solution for chat data management, with inputs including chat account credentials and outputs including unified chat data and MCP tool access.

Canonical page: https://skillsregistry.net/skills/echoedinvoker-chatmux  
JSON: https://api.skillsregistry.net/v1/skills/echoedinvoker-chatmux

## Description

Local-first MCP server that puts your own LINE and Telegram chats behind one data layer — a daemon on your machine logs in with your own account, stores messages to JSONL + SQLite/FTS5, and exposes 6 MCP tools over streamable HTTP on 127.0.0.1. Not a hosted service and not an npx one-liner: you clone the repo, run the daemon, and log in yourself.

## Trust

- **Trust score (0–1):** 0.39
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ebp42fhbe4)
- **Repository:** <https://github.com/echoedinvoker/chatmux>

## 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": "echoedinvoker-chatmux"
    }
  }
}
```

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