local-embedding

Agent Skills › matrixorigin/memoria › local-embedding

local-embedding

GitHub

指导在本地通过 ONNX Runtime 构建和配置离线嵌入模型，支持自定义模型选择与参数设置，无需 API Key，适用于对隐私有严格要求或无网络环境的场景。

skills/local-embedding/SKILL.md matrixorigin/memoria

Trigger Scenarios

需要在本地运行文本嵌入避免使用远程 API 以保护隐私在无网络环境下进行数据处理

Install

npx skills add matrixorigin/memoria --skill local-embedding -g -y

More Options

Use without installing

npx skills use matrixorigin/memoria@local-embedding

指定 Agent (Claude Code)

npx skills add matrixorigin/memoria --skill local-embedding -a claude-code -g -y

安装 repo 全部 skill

npx skills add matrixorigin/memoria --all -g -y

预览 repo 内 skill

npx skills add matrixorigin/memoria --list

SKILL.md

Frontmatter

{
    "name": "local-embedding",
    "description": "Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key."
}

Build from Source

Pre-built binaries do NOT include local embedding.

cd Memoria
make build-local
sudo cp memoria/target/release/memoria /usr/local/bin/

Binary is ~50-80MB (bundles ONNX Runtime). Expected.

Configure

memoria init --tool kiro    # No --embedding-* flags needed

Leave EMBEDDING_* env vars empty in mcp.json → local embedding is the default.

How It Works

First query → model downloads to ~/.cache/fastembed/ (~30MB default)
Model loads via ONNX Runtime (~3-5s)
Subsequent queries are fast (in-process)

Models

Model	Dim	Size	Notes
`all-MiniLM-L6-v2`	384	~30MB	Default. Fast, English
`BAAI/bge-m3`	1024	~1.2GB	Best quality, multilingual

Change model in mcp.json env block:

{ "EMBEDDING_MODEL": "BAAI/bge-m3", "EMBEDDING_DIM": "1024" }

⚠️ Choose BEFORE first startup. Dimension is locked into schema.

When to Use

	Local	Remote (OpenAI/SiliconFlow)
Privacy	✅ Offline	⚠️ Text sent to API
Cost	Free	API key
First query	~3-5s	Fast
Build	From source	Pre-built works
Offline	✅	❌

Recommendation: Use remote unless you need offline/strict privacy.

Troubleshooting

Problem	Fix
"compiled without local-embedding"	Build from source: `make build-local`
Model download fails	Set `HF_ENDPOINT` for mirror, or manually download to `~/.cache/fastembed/`
High memory	Default ~100MB. `bge-m3` ~1-2GB. Choose based on available RAM