# embeddings-runtime-stinger

embeddings-runtime-stinger helps pick and run an embedding model: OpenAI, Cohere, Voyage AI or a self-hosted alternative. Triggers on model selection, swaps, batching and caching fixes.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/embeddings-runtime-stinger/SKILL.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/embeddings-runtime-stinger

## What it does

The skill routes each request into one mode: provider selection, OpenAI, Cohere or Voyage AI specifics, batching, caching, or maintaining a self-hosted daemon running nomic-embed-text-v1.5. Every mode points to a guide producing one concrete output — a model recommendation, a dimension-swap plan, a batching or caching fix, or a config snippet.

The self-hosted daemon talks over a Unix socket using an NDJSON protocol and runs a q8-quantized model at 768 dimensions. Separate guides cover daemon warmup, the IPC protocol, crash recovery, and the call between running local embeddings versus falling back to BM25 lexical search.

Whatever dimension gets chosen has to match the vector store schema, pgvector or Deep Lake, or the two fall out of sync. Column and index mechanics themselves belong to a different skill, vector-store-stinger.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install data-and-ai-tools@wasp-nest
```
This installs the whole data-and-ai-tools plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill embeddings-runtime-stinger -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/embeddings-runtime-stinger/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/embeddings-runtime-stinger/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill embeddings-runtime-stinger -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/embeddings-runtime-stinger/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill embeddings-runtime-stinger -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/embeddings-runtime-stinger/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install legioncodeinc/vibe-coding-tools plugins/data-and-ai-tools/skills/embeddings-runtime-stinger
```

2. **Manually: put the files in place**
- File: `.github/skills/embeddings-runtime-stinger/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill embeddings-runtime-stinger -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/legioncodeinc/vibe-coding-tools --path plugins/data-and-ai-tools/skills/embeddings-runtime-stinger
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/embeddings-runtime-stinger/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/embeddings-runtime-stinger/SKILL.md

## When to use it
- choose between OpenAI, Cohere, Voyage AI and a self-hosted model
- plan an embedding model swap including a dimension migration
- set up batching for embedding API calls
- cache embeddings so identical text isn't re-embedded
- fix a stuck local embedding daemon

## Example prompts
- Which embedding model should I use — OpenAI, Cohere, or Voyage AI?
- Write a model-swap plan that accounts for the dimension change
- The local embedding daemon won't start, figure out why

## Similar
- [grepai-embeddings-openai](https://affpapa.org/en/nevibecode/skills/grepai-embeddings-openai.md) — skill · 560 installs
- [venice-embeddings](https://affpapa.org/en/nevibecode/skills/venice-embeddings.md) — skill · ★ 176 repo stars
- [grepai-embeddings-lmstudio](https://affpapa.org/en/nevibecode/skills/grepai-embeddings-lmstudio.md) — skill · 568 installs
- [langchain4j-vector-stores-configuration](https://affpapa.org/en/nevibecode/skills/langchain4j-vector-stores-configuration.md) — skill · 3900 installs
- [clip-aware-embeddings](https://affpapa.org/en/nevibecode/skills/clip-aware-embeddings.md) — skill · 188 installs
- [rag-retrieval](https://affpapa.org/en/nevibecode/skills/rag-retrieval.md) — skill · 1500 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
