Agent skill

Local Embedding

Run embedding on-device with ONNX Runtime. An agent skill from matrixorigin/memoria.

Apache-2.0Auto-check: notesAI & LLM Engineering

Install Local Embedding

skills CLI

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

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/local-embedding .claude/skills/local-embedding && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .claude/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add matrixorigin/memoria --skill local-embedding -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/local-embedding .agents/skills/local-embedding && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .agents/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matrixorigin/memoria --skill local-embedding -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/local-embedding .cursor/skills/local-embedding && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .cursor/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/matrixorigin/memoria.git --path skills/local-embedding

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add matrixorigin/memoria --skill local-embedding -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/local-embedding .gemini/skills/local-embedding && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .gemini/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add matrixorigin/memoria --skill local-embedding -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/local-embedding .github/skills/local-embedding && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .github/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add matrixorigin/memoria --skill local-embedding -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install matrixorigin/memoria local-embedding --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/matrixorigin/memoria.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/local-embedding .opencode/skills/local-embedding && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "local-embedding" agent skill from https://github.com/matrixorigin/memoria/tree/main/skills/local-embedding into .opencode/skills/local-embedding/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "local-embedding", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: local-embedding
GitHub stars: 607
Token cost: ~444 tokens
SKILL.md length: 155 words
Files: 1
Skills in repo: 9
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Run embedding on-device with ONNX Runtime. An agent skill from matrixorigin/memoria.

Works in 3 steps: First query → model downloads to… → Model loads via ONNX Runtime (~3-5s) → Subsequent queries are fast (in-process)
Setting up local embedding without an API key
SKILL.md covers Build from Source, Configure, How It Works and Models, plus 2 more sections
Calls make

What it does

Local Embedding is an agent skill from matrixorigin/memoria. Run embedding on-device with ONNX Runtime. Build from source, model selection, offline mode. Use when setting up local embedding without an API key.

Its SKILL.md is about 440 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Embeddings. It works with ONNX. The repository describes itself as: Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context. The licence is Apache-2.0.

When your agent uses it

Setting up local embedding without an API key
Tasks that involve Embeddings

Example prompts

“/local-embedding”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 81c5cc6. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- make
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Local Embedding loads about 444 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 155 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~41
When it runs · the whole SKILL.md, loaded when a task matches: ~444

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteRuns commands with sudoSKILL.md:13

sudo cp memoria/target/release/memoria /usr/local/bin/

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from matrixorigin/memoria at commit 81c5cc6, republished under its Apache-2.0 licence (© matrixorigin). 155 words, ~444 tokens.

Download SKILL.mdSave it as .claude/skills/local-embedding/SKILL.md (or your agent's skills folder).

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.

bash

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

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

Configure

bash

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:

json

{ "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

Files

Just SKILL.md in skills/local-embedding of matrixorigin/memoria.

Open the folder on GitHubat commit 81c5cc6

Compare with similar skills

Local Embedding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Local Embedding compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Local Embedding this skillmatrixorigin/memoria	607	—	~444	Automated safety check: Notes	Apache-2.0	today
Memory Bridgeruvnet/ruflo	74k	—	~601	Automated safety check: Notes	MIT	today
Vector Embedruvnet/ruflo	74k	—	~591	Automated safety check: Notes	MIT	today
Tao Finetune ClipNVIDIA/skills	3.5k	—	~4k	Automated safety check: Notes	Apache-2.0	today
Backend Export OptimizationVectorSpaceLab/AREX-Skill	328	—	~766	Automated safety check: Pass	Apache-2.0	1 mo ago
Re AI Modeldslsdzc/rev-skills	117	—	~2.4k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

Memory Bridge
ruvnet/ruflo
Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
74k GitHub stars~601 tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Vector Embed
ruvnet/ruflo
Generate embeddings via npx ruvector@0.2.25 embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index
74k GitHub stars~591 tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Tao Finetune Clip
NVIDIA/skills
Official
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment.
3.5k GitHub stars~4k tokensUpdated today
AI & LLM EngineeringAuto-check: notes
Backend Export Optimization
VectorSpaceLab/AREX-Skill
A skill your agent uses when selecting Sentence Transformers inference backends or exporting/optimizing models for PyTorch, ONNX, or OpenVINO.
328 GitHub stars~766 tokensUpdated 1 mo ago
AI & LLM EngineeringAuto-check passed
Re AI Model
dslsdzc/rev-skills
AI 模型文件逆向与静态分析：ONNX/PyTorch/Safetensors/TFLite 格式解析、网络结构还原、权重提取、文件级水印分析（权重 pattern/metadata/tensor hash/embedding 异常）。
117 GitHub stars~2.4k tokensUpdated 2 days ago
AI & LLM EngineeringAuto-check passed
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
13k GitHub starsUsed in 9 repos~3.3k tokens
AI & LLM EngineeringAuto-check passed

Questions about Local Embedding

What does Local Embedding do?

Run embedding on-device with ONNX Runtime. An agent skill from matrixorigin/memoria. Local Embedding is an agent skill from matrixorigin/memoria. Run embedding on-device with ONNX Runtime.

When should I use Local Embedding?

Local Embedding fits situations like: setting up local embedding without an API key; tasks that involve Embeddings.

How do I install Local Embedding in Claude Code?

Run `npx skills add matrixorigin/memoria --skill local-embedding -a claude-code`. Or copy the skill folder (skills/local-embedding in matrixorigin/memoria) into .claude/skills/local-embedding in your project. Claude Code loads it when a task matches its description.

How do I install Local Embedding in Codex?

Run `npx skills add matrixorigin/memoria --skill local-embedding -a codex`. Or copy the skill folder (skills/local-embedding in matrixorigin/memoria) into .agents/skills/local-embedding in your project. Codex loads it when a task matches its description.

Can I use Local Embedding in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add matrixorigin/memoria --skill local-embedding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-embedding, .gemini/skills/local-embedding, .github/skills/local-embedding and .opencode/skills/local-embedding in your project.

What does Local Embedding need to run?

Going by SKILL.md and its folder, Local Embedding needs the command-line tools its instructions call (make).

Does Local Embedding access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Local Embedding safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Local Embedding use?

Local Embedding is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Local Embedding use?

About 444 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Local Embedding?

Skills that share tags, products or a category with Local Embedding: Memory Bridge (ruvnet/ruflo, 74k stars), Vector Embed (ruvnet/ruflo, 74k stars), Tao Finetune Clip (NVIDIA/skills, 3.5k stars) and Backend Export Optimization (VectorSpaceLab/AREX-Skill, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Embedding?

matrixorigin (a GitHub organization) maintains it in matrixorigin/memoria, which has 607 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 7, 2026.

Source: matrixorigin/memoria on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Local Embedding

Install Local Embedding

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Build from Source

Configure

How It Works

Models

When to Use

Troubleshooting

Files

Compare with similar skills

Similar skills

Memory Bridge

Vector Embed

Tao Finetune Clip

Backend Export Optimization

Re AI Model

Segment Anything Model Guide

More from matrixorigin/memoria

Thememoria

API Reference

Architecture

Deployment

Plugin Development

Release

Questions about Local Embedding

Install Local Embedding

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Build from Source

Configure

How It Works

Models

When to Use

Troubleshooting

Files

Compare with similar skills

Similar skills

More from matrixorigin/memoria

Related

Questions about Local Embedding