Give your Hermes Agent live web search, news, page reading, sitemap discovery, and trending topics through Search1API.
hermes plugins install superagents-lab/hermes-search1api --enable
export SEARCH1API_KEY="your-key" # https://s1.dev — 100 free creditsSEARCH1API_API_KEY is also accepted. No other dependencies: the official
search1api Python SDK is vendored
into this repo, and its only requirement (httpx) is already a Hermes core
dependency.
| Tool | What it does |
|---|---|
search1api_search |
Live web search — freshness (time_range), domain filters (include_sites/exclude_sites), engine choice (search_service), optional full-page retrieval (crawl_results) |
search1api_news |
News search with the same filters |
search1api_ask |
Natural-language search with automatic routing and relevance ranking (5 credits) |
search1api_crawl |
Read one public URL as clean Markdown |
search1api_sitemap |
Enumerate a site's URLs |
search1api_trending |
Trending GitHub repos / Hacker News stories |
All tools return JSON. Errors come back as
{"success": false, "error": {"type", "message", "status_code?"}}.
A bundled skill (plugin:search1api) teaches the agent when to pick each tool;
load it with skill_view("plugin:search1api").
__init__.py— plugin entry point (register(ctx)), tool handlerssearch1api/— vendored SDK (synced from PyPI viascripts/sync_sdk.sh)skills/search1api/SKILL.md— bundled skillplugin.yaml— Hermes plugin manifest
- Search1API: https://s1.dev · Terms: https://blog.s1.dev/pages/terms · Privacy: https://s1.dev/privacy
- Maintained by SuperAgents, LLC
MIT
Search supports bingcn, yandex, and grokipedia; sogou is removed.
Search and news support day, week, month, and year. Search accepts
page on engines with native pagination.
The default Ask tool accepts only a natural-language query. The server
chooses engines and a time window and returns query, intent, ranked
results, and errors. Ask results include source and relevance; this
endpoint returns search results rather than a generated answer. Each call
costs 5 credits. Use ordinary search when the engine and keywords are known.
Engine-specific search/news attributes stay inside optional per-result
metadata: GitHub uses kind, stars, language, and num_comments;
Hacker News news results use story_url, points, and num_comments.
published_date stays optional at the result top level. Zero counts are
preserved and unavailable fields are omitted. Credit Grokipedia results as
"Powered by xAI".
search1api_ask is registered by default. The vendored SDK is the exact
published Python SDK 0.4.0; no extra pip installation is needed.