How do I install the Zvec Local RAG Service skill?

Run npx skillmds@latest add johnalbertini14-glitch/zvec-local-rag-service in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Zvec Local RAG Service safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Zvec Local RAG Service?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Zvec Local RAG Service free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Zvec Local RAG Service?

johnalbertini14-glitch (@johnalbertini14-glitch) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Zvec Local RAG Service by johnalbertini14-glitch

Name: Zvec Local RAG Service
Rating: 4.2 (5 reviews)
Author: johnalbertini14-glitch

Zvec Local RAG Service

Operate an always-on local semantic-search service using zvec + Ollama embeddings. Use when you need to ingest .txt/.md files, run meaning-based search via HTTP endpoints (/health, /ingest, /search), and keep the service running on macOS (launchd) or manually. Includes service code, launchd template, and management scripts.

File contents

zvec-local-rag-service

Run local RAG search with Ollama embeddings and zvec.

Included files

scripts/rag-service.mjs → HTTP service implementation
scripts/manage.sh → bootstrap/start/stop/restart/health/ingest/search
references/launchd.plist.template → macOS LaunchAgent template

Prerequisites

Node.js 18+
Ollama daemon running
Embedding model (default): mxbai-embed-large

Prepare model once:

ollama pull mxbai-embed-large

Quick start

From the skill directory:

scripts/manage.sh bootstrap
scripts/manage.sh install-launchd   # writes plist, inspect once
scripts/manage.sh start
scripts/manage.sh health

Ingest and search:

scripts/manage.sh ingest ./docs
scripts/manage.sh search "your query"

Install + smoke test (copy/paste)

# 1) prerequisites
ollama pull mxbai-embed-large

# 2) bootstrap and start service
scripts/manage.sh bootstrap
scripts/manage.sh install-launchd
scripts/manage.sh start

# 3) verify health
scripts/manage.sh health

# 4) create tiny test corpus
mkdir -p ./docs
cat > ./docs/sample.md <<'EOF'
Zvec + Ollama enables local semantic search.
EOF

# 5) ingest + query
scripts/manage.sh ingest ./docs
scripts/manage.sh search "local semantic search with ollama"

Endpoints

GET /health
POST /ingest with { "dir": "./docs", "reset": true }
POST /search with { "query": "...", "topk": 5 }

Persistence (macOS launchd)

Install and enable LaunchAgent:

scripts/manage.sh install-launchd
scripts/manage.sh start
scripts/manage.sh status

Remove LaunchAgent:

scripts/manage.sh uninstall-launchd

Always inspect generated plist before enabling persistence:

~/Library/LaunchAgents/com.openclaw.zvec-rag-service.plist

Config via env vars

RAG_HOST (default 127.0.0.1)
RAG_PORT (default 8787)
OLLAMA_URL (default http://127.0.0.1:11434)
OLLAMA_EMBED_MODEL (default mxbai-embed-large)
RAG_BASE_DIR (default ~/.openclaw/data/zvec-rag-service)
ALLOW_REMOTE_OLLAMA (default false, blocks non-local OLLAMA_URL)
ALLOW_NON_LOOPBACK_HOST (default false, blocks externally reachable bind host)

Notes

Secure defaults: loopback-only service + loopback-only Ollama.
Remote embedding/host binding require explicit opt-in env flags.
launchd operations are macOS-specific. On non-macOS, run with scripts/manage.sh start (manual mode).

---name: zvec-local-rag-servicedescription: Operate an always-on local semantic-search service using zvec + Ollama embeddings. Use when you need to ingest .txt/.md files, run meaning-based search via HTTP endpoints (/health, /ingest, /search), and keep the service running on macOS (launchd) or manually. Includes service code, launchd template, and management scripts.---# zvec-local-rag-serviceRun local RAG search with Ollama embeddings and zvec.## Included files- `scripts/rag-service.mjs` → HTTP service implementation- `scripts/manage.sh` → bootstrap/start/stop/restart/health/ingest/search- `references/launchd.plist.template` → macOS LaunchAgent template## Prerequisites- Node.js 18+- Ollama daemon running- Embedding model (default): `mxbai-embed-large`Prepare model once:```bashollama pull mxbai-embed-large```## Quick startFrom the skill directory:```bashscripts/manage.sh bootstrapscripts/manage.sh install-launchd # writes plist, inspect oncescripts/manage.sh startscripts/manage.sh health```Ingest and search:```bashscripts/manage.sh ingest ./docsscripts/manage.sh search "your query"```## Install + smoke test (copy/paste)```bash# 1) prerequisitesollama pull mxbai-embed-large# 2) bootstrap and start servicescripts/manage.sh bootstrapscripts/manage.sh install-launchdscripts/manage.sh start# 3) verify healthscripts/manage.sh health# 4) create tiny test corpusmkdir -p ./docscat > ./docs/sample.md <<'EOF'Zvec + Ollama enables local semantic search.EOF# 5) ingest + queryscripts/manage.sh ingest ./docsscripts/manage.sh search "local semantic search with ollama"```## Endpoints- `GET /health`- `POST /ingest` with `{ "dir": "./docs", "reset": true }`- `POST /search` with `{ "query": "...", "topk": 5 }`## Persistence (macOS launchd)Install and enable LaunchAgent:```bashscripts/manage.sh install-launchdscripts/manage.sh startscripts/manage.sh status```Remove LaunchAgent:```bashscripts/manage.sh uninstall-launchd```Always inspect generated plist before enabling persistence:- `~/Library/LaunchAgents/com.openclaw.zvec-rag-service.plist`## Config via env vars- `RAG_HOST` (default `127.0.0.1`)- `RAG_PORT` (default `8787`)- `OLLAMA_URL` (default `http://127.0.0.1:11434`)- `OLLAMA_EMBED_MODEL` (default `mxbai-embed-large`)- `RAG_BASE_DIR` (default `~/.openclaw/data/zvec-rag-service`)- `ALLOW_REMOTE_OLLAMA` (default `false`, blocks non-local OLLAMA_URL)- `ALLOW_NON_LOOPBACK_HOST` (default `false`, blocks externally reachable bind host)## Notes- Secure defaults: loopback-only service + loopback-only Ollama.- Remote embedding/host binding require explicit opt-in env flags.- `launchd` operations are macOS-specific. On non-macOS, run with `scripts/manage.sh start` (manual mode).

Frequently asked questions