Academy → Developer GuideOfficial documentation · Arabic guidance

Web Search Provider Plugins

إضافات مزوّد البحث

Advanced7 min readLesson 242 questions✓ 2026-08-18
Before you read

What this page is, and what it holds.

This page covers Web Search Provider Plugins. You will use hermes tools here; about 7 minutes to read. A plugin runs with the agent's full permissions. Do not install one you cannot read.

12sections
9code examples
3tables
1commands
1,238source words
The official one-line description

How to build a web-search/extract/crawl backend plugin for Hermes Agent

What you will be able to do

Outcomes taken from this page, not a template.

  • Understand what الإضافات is and when you need it.
  • Run hermes tools and understand what happens next.
  • Read the table and take only the row that applies to you.
Identifiers you will meet

Exactly as they appear in Hermes.

Commands
  • hermes tools
Page map

Jump to the part you need.

  1. 01How discovery works
  2. 02Directory structure
  3. 03The WebSearchProvider ABC
  4. 04plugin.yaml
  5. 05ABC reference
  6. 06Response shape
  7. 07Capability flags
  8. 08How Hermes wires it into the tools
  9. 09Lazy-installing optional dependencies
  10. 10Reference implementations
  11. 11Distribute via pip
  12. 12Related pages
The full official page

Nothing summarised away.

The documentation body below is reproduced from the official source so commands and identifiers stay exact. Each section carries a short note describing what it contains.

Web-search provider plugins register a backend that services web_search, web_extract, and (optionally) deep-crawl tool calls. Built-in providers — Firecrawl, SearXNG, Tavily, Exa, Parallel, Brave Search (free tier), xAI, and DDGS — all ship as plugins under plugins/web/<name>/. You can add a new one, or override a bundled one, by dropping a directory next to them.

How discovery works

Commands you type in a terminal. Understand what one does before copying it. Commands here: hermes tools.

Hermes scans for web-search backends in three places:

  1. Bundled — <repo>/plugins/web/<name>/ (auto-loaded with kind: backend, always available)
  2. User — ~/.hermes/plugins/web/<name>/ (opt-in via plugins.enabled or hermes plugins enable <name>)
  3. Pip — packages declaring a hermes_agent.plugins entry point

Each plugin's register(ctx) function calls ctx.register_web_search_provider(...) — that puts the instance into the registry in agent/web_search_registry.py. The active provider for each capability is picked by config:

CapabilityConfig keyFalls back to
web_searchweb.search_backendweb.backend
web_extractweb.extract_backendweb.backend
Deep crawl modes inside web_extractweb.extract_backendweb.backend

When neither key is set, Hermes auto-detects the backend from whichever API key/URL is present in the environment. hermes tools walks users through selection.

Directory structure

Explains the idea itself. Read it slowly; the later sections build on it.

Text4 lines
plugins/web/my-backend/
├── __init__.py     # register() entry point
├── provider.py     # WebSearchProvider subclass
└── plugin.yaml     # Manifest with kind: backend and provides_web_providers

brave_free/ and ddgs/ are the smallest in-tree references — brave_free for an API-key-gated search-only provider, ddgs for a no-key provider that lazy-installs its SDK.

The WebSearchProvider ABC

Explains the idea itself. Read it slowly; the later sections build on it.

Subclass agent.web_search_provider.WebSearchProvider. The only required members are name, is_available(), and whichever of search() / extract() you implement. (Deep crawling is not a separate method — it's a mode of extract().)

Python65 lines
# plugins/web/my-backend/provider.py
from __future__ import annotations


from typing import Any, Dict, List

from agent.web_search_provider import WebSearchProvider


class MyBackendWebSearchProvider(WebSearchProvider):
    """Minimal search-only provider against the My Backend HTTP API."""

    @property
    def name(self) -> str:
        # Stable id used in web.search_backend / web.extract_backend / web.backend
        # config keys. Lowercase, no spaces; hyphens permitted.
        return "my-backend"

    @property
    def display_name(self) -> str:
        # Human label shown in `hermes tools`. Defaults to `name`.
        return "My Backend"

    def is_available(self) -> bool:
        # Cheap check — env var present, optional dep importable, etc.
        # MUST NOT make network calls (runs on every `hermes tools` paint).
        return bool(os.getenv("MY_BACKEND_API_KEY", "").strip())

    def supports_search(self) -> bool:
        return True

    def supports_extract(self) -> bool:
        return False

    def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
        import httpx

        api_key = os.environ["MY_BACKEND_API_KEY"]
        try:
            resp = httpx.get(
                "https://api.example.com/search",
                params={"q": query, "count": max(1, min(int(limit), 20))},
                headers={"Authorization": f"Bearer {api_key}"},
                timeout=15,
            )
            resp.raise_for_status()
            data = resp.json()
        except httpx.HTTPError as exc:
            return {"success": False, "error": str(exc)}

        # Response shape is fixed — see "Response shape" below.
        return {
            "success": True,
            "data": {
                "web": [
                    {
                        "title": item.get("title", ""),
                        "url": item.get("url", ""),
                        "description": item.get("snippet", ""),
                        "position": idx + 1,
                    }
                    for idx, item in enumerate(data.get("results", []))
                ],
            },
        }
Python7 lines
# plugins/web/my-backend/__init__.py
from plugins.web.my_backend.provider import MyBackendWebSearchProvider


def register(ctx) -> None:
    """Plugin entry point — called once at load time."""
    ctx.register_web_search_provider(MyBackendWebSearchProvider())

plugin.yaml

Settings you configure once. Change one at a time so you can see what each does.

YAML9 lines
name: web-my-backend
version: 1.0.0
description: "My Backend web search — Bearer-auth REST API"
author: Your Name
kind: backend
provides_web_providers:
  - my-backend
requires_env:
  - MY_BACKEND_API_KEY
KeyPurpose
kind: backendRoutes the plugin through the backend-loading path
provides_web_providersList of provider names this plugin registers — used by the loader to advertise the plugin in hermes tools even before register() runs
requires_envInteractive credential prompt during hermes plugins install (see Build a Hermes Plugin for the rich format)

ABC reference

A lookup table. Do not read it all; find the row that applies to you.

Full contract in agent/web_search_provider.py. Methods you may override:

MemberRequiredDefaultPurpose
name✅—Stable id used in web.*_backend config
display_name—nameLabel shown in hermes tools
is_available()✅—Cheap availability gate — env vars, optional deps
supports_search()—TrueCapability flag for web_search routing
supports_extract()—FalseCapability flag for web_extract routing
search(query, limit)conditionalraisesRequired when supports_search() returns True
extract(urls, **kwargs)conditionalraisesRequired when supports_extract() returns True

Providers can advertise multiple capabilities from a single class — Firecrawl, Tavily, Exa, and Parallel all implement both search and extract. Brave Search and DDGS are search-only; SearXNG is search-only with a documented "pair me with an extract provider" workflow.

Response shape

Explains the idea itself. Read it slowly; the later sections build on it.

The tool wrapper expects a fixed envelope so it doesn't have to translate between backends.

Search success:

Python9 lines
{
    "success": True,
    "data": {
        "web": [
            {"title": str, "url": str, "description": str, "position": int},
            ...
        ],
    },
}

Extract success:

Python14 lines
{
    "success": True,
    "data": [
        {
            "url": str,
            "title": str,
            "content": str,
            "raw_content": str,
            "metadata": dict,    # optional
            "error": str,        # optional, only on per-URL failure
        },
        ...
    ],
}

Either capability, on failure:

Python1 line
{"success": False, "error": "human-readable message"}

Both search() and extract() may be async def — the dispatcher detects coroutine functions via inspect.iscoroutinefunction and awaits accordingly. Sync implementations that do blocking I/O (HTTP, SDK calls) are fine for small backends; the dispatcher handles threading.

Capability flags

Settings you configure once. Change one at a time so you can see what each does.

Hermes routes calls to the right provider based on the supports_* flags. A common multi-provider setup:

YAML4 lines
# ~/.hermes/config.yaml
web:
  search_backend: "brave-free"     # search-only, fast, free 2k/mo
  extract_backend: "firecrawl"     # extract + crawl, paid quota

When web.search_backend or web.extract_backend aren't set, both fall through to web.backend. When that's also unset, Hermes picks the first available provider that supports the requested capability based on env-var presence.

If your provider only supports one capability, leave the other flags at their default (False) and the registry will skip it for that tool — users won't see misleading "provider X failed" errors when they're using X only for search and asking the agent to extract.

How Hermes wires it into the tools

Commands you type in a terminal. Understand what one does before copying it. Commands here: hermes tools.

The web_search and web_extract tools live in tools/web_tools.py. At call time they:

  1. Read the relevant config key (web.search_backend for web_search, web.extract_backend for web_extract)
  2. Ask the registry for the provider with that name
  3. Check is_available() and the matching supports_*() flag
  4. Dispatch to search() / extract() (deep crawl runs as a mode inside extract()), awaiting if the method is a coroutine
  5. JSON-serialize the response envelope and hand it back to the LLM

Errors surface as the tool result; the LLM decides how to explain them. If no provider is registered (or every available one fails the capability gate), the tool returns a helpful error pointing at hermes tools.

Lazy-installing optional dependencies

Ordered, practical steps. Run one and confirm it worked before moving on.

If your provider wraps a third-party SDK (like DDGS does with the ddgs package), don't import it at module top level. Use tools.lazy_deps.ensure(...) inside is_available() or search() — Hermes will install the package on first use, gated by security.allow_lazy_installs. See Build a Hermes Plugin → Lazy-install for the security model.

Reference implementations

Explains the idea itself. Read it slowly; the later sections build on it.

  • plugins/web/brave_free/ — small, API-key-gated, search-only HTTP provider. Good starting template.
  • plugins/web/ddgs/ — no-key provider that lazy-installs its SDK. Useful pattern for backends that wrap a Python package.
  • plugins/web/firecrawl/ — full multi-capability provider (search + extract + crawl) with multiple format modes.
  • plugins/web/searxng/ — self-hosted, URL-configured backend with no auth.
  • plugins/web/xai/ — LLM-backed search via Grok's server-side web_search tool. Shows how to reuse an existing OAuth/env-var credential surface (tools/xai_http.py) without adding new env vars, and how to write a cheap is_available() that honors the no-network contract.

Distribute via pip

Explains the idea itself. Read it slowly; the later sections build on it.

TOML3 lines
# pyproject.toml
[project.entry-points."hermes_agent.plugins"]
my-backend-web = "my_backend_web_package"

my_backend_web_package must expose a top-level register function. See Distribute via pip in the general plugin guide for the full setup.

Knowledge check

2 questions answered by this page alone.

Every option is a real identifier from the Hermes documentation. The wrong ones are real too, just from other pages.

1. Which of these headings does not appear in this lesson?
2. Which configuration key appears in this lesson's examples?