This runs SearXNG locally in a container and lets you query multiple search engines through a single JSON API. It's built for programmatic access to web search and package repositories like crates.io, npm, and others, though PyPI doesn't work and needs a workaround. The included start-searxng script handles container setup automatically. Honestly most useful when you need to aggregate search results in scripts or AI workflows without hitting rate limits, since it's all running on localhost. The JSON responses are clean and include which engines contributed to each result, making it easy to filter and process.
npx -y skills add ypares/agent-skills --skill searxng-search --agent claude-codeInstalls into .claude/skills of the current project.
SearXNG is a privacy-respecting metasearch engine that you can run locally. It aggregates results from multiple search engines and package repositories, returning clean JSON output.
Start SearXNG:
start-searxng --detach
This will:
http://localhost:8888Stop SearXNG:
podman stop searxng # or: docker stop searxng
Custom port:
start-searxng --port 9999 --detach
| Task | Command | Category |
|---|---|---|
| General web search | curl "http://localhost:8888/search?q=<query>&format=json" | general |
| Search Cargo/crates.io | curl "http://localhost:8888/search?q=<crate>&format=json&categories=cargo" | cargo |
| Search npm packages | curl "http://localhost:8888/search?q=<pkg>&format=json&categories=packages" | packages |
| Search code repositories | curl "http://localhost:8888/search?q=<query>&format=json&categories=repos" | repos |
| Search IT resources | curl "http://localhost:8888/search?q=<query>&format=json&categories=it" | it |
| Limit results | Add &limit=N to URL | - |
| Multiple categories | &categories=cat1,cat2 | - |
Run to see all categories:
curl -s "http://localhost:8888/config" | jq '.categories'
Notable categories:
See package-engine-status.md for comprehensive package search testing results.
{
"query": "search term",
"number_of_results": 0,
"results": [
{
"url": "https://example.com",
"title": "Result Title",
"content": "Snippet of content...",
"publishedDate": "2025-01-01T00:00:00",
"engine": "duckduckgo",
"engines": ["duckduckgo", "startpage"],
"score": 3.0,
"category": "general"
}
],
"answers": [], // Direct answers/infoboxes
"suggestions": [], // Search suggestions
"corrections": [], // Query corrections
"infoboxes": [], // Knowledge panels
"unresponsive_engines": []
}
Cargo/Rust crates:
curl -s "http://localhost:8888/search?q=tokio&format=json&categories=cargo" | \
jq '.results[] | {title, url, content}'
npm packages:
curl -s "http://localhost:8888/search?q=express&format=json&categories=packages" | \
jq '.results[] | select(.engines[] == "npm") | {title, url, content}'
PyPI packages (workaround - see below):
# PyPI engine is enabled but not returning results in current SearXNG config
# Use direct API or qypi CLI instead (see PyPI Workaround section)
IT/Tech search:
curl -s "http://localhost:8888/search?q=rust+async&format=json&categories=it" | \
jq '.results[0:5] | .[] | {title, url, engines}'
GitHub repositories:
curl -s "http://localhost:8888/search?q=machine+learning&format=json&categories=repos" | \
jq '.results[] | select(.engines[] == "github") | {title, url}'
Get top 3 results:
curl -s "http://localhost:8888/search?q=rust+ownership&format=json" | \
jq '.results[0:3] | .[] | {title, url, content}'
Check which engines returned results:
curl -s "http://localhost:8888/search?q=python&format=json" | \
jq '.results[0].engines'
Get answer boxes/infoboxes:
curl -s "http://localhost:8888/search?q=rust+language&format=json" | \
jq '.infoboxes, .answers'
Since PyPI is not returning results in SearXNG (despite being enabled), use these alternatives:
# Search (limited to simple package name matching)
curl -s "https://pypi.org/pypi/<package>/json" | jq '.info | {name, summary, version, home_page}'
# Example:
curl -s "https://pypi.org/pypi/requests/json" | jq '.info.summary'
# Install
uvx qypi search pandas --json
# Get package info
uvx qypi info requests --json
# List releases
uvx qypi releases flask --json
See references/pypi-direct-search.md for more details.
Create a helper function:
def searx [
query: string,
--category (-c): string = "general",
--limit (-l): int = 10
] {
http get $"http://localhost:8888/search?q=($query | url encode)&format=json&categories=($category)"
| get results
| first $limit
| select title url content engines
}
Usage:
searx "tokio async" --category cargo --limit 5
searx "flask tutorial" --category general
Check SearXNG config:
curl -s "http://localhost:8888/config" | jq '.engines[] | select(.name == "pypi")'
Check for engine errors:
curl -s "http://localhost:8888/search?q=test&format=json" | jq '.unresponsive_engines'
Test specific engine:
curl -s "http://localhost:8888/search?q=flask&format=json&engines=pypi" | jq .
categories=packages or categories=it which also include crates.ioThe start-searxng script creates a minimal configuration automatically:
start-searxng --help
Default config includes:
use_default_settings: true (inherits all SearXNG defaults)start-searxng --config /path/to/your/config/dir
Your config directory should contain settings.yml.
# Create config
mkdir -p /tmp/searxng-config
cat > /tmp/searxng-config/settings.yml << 'EOF'
use_default_settings: true
search:
formats:
- html
- json
server:
secret_key: "change-me-in-production"
bind_address: "0.0.0.0"
port: 8080
EOF
# Start with podman
podman run --rm -d --name searxng \
-p 8888:8080 \
-v /tmp/searxng-config:/etc/searxng:Z \
docker.io/searxng/searxng:latest
# Or with docker
docker run --rm -d --name searxng \
-p 8888:8080 \
-v /tmp/searxng-config:/etc/searxng \
docker.io/searxng/searxng:latest
podman logs searxng # or: docker logs searxng
See SearXNG Settings Documentation for all options.
Minimal config to add JSON output to defaults:
use_default_settings: true
search:
formats:
- html
- json
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot