feat(web): add SearXNG as a native search-only backend

Adds SearXNG as a free, self-hosted web search provider.  SearXNG is a
privacy-respecting metasearch engine that requires no API key — just a
running instance and SEARXNG_URL pointing at it.

## What this adds

- `tools/web_providers/searxng.py` — `SearXNGSearchProvider` implementing
  `WebSearchProvider` (search only; no extract capability)
- `_is_backend_available("searxng")` — gates on SEARXNG_URL
- `_get_backend()` — accepts "searxng" as a configured value; adds it to
  auto-detect candidates (lower priority than paid services)
- `web_search_tool` — dispatches to SearXNG when it is the active backend
- `check_web_api_key()` — includes SearXNG in availability check
- `OPTIONAL_ENV_VARS["SEARXNG_URL"]` — registered with tools=["web_search"]
- `tools_config.py` — SearXNG appears in the `hermes tools` provider picker
- `nous_subscription.py` — `direct_searxng` detection, web_active / web_available
- `setup.py` — SEARXNG_URL listed in the missing-credential hint
- 23 tests covering: is_configured, happy-path search, score sorting, limit,
  HTTP/request errors, _is_backend_available, _get_backend, check_web_api_key

## Config

```yaml
# Use SearXNG for search, any paid provider for extract
web:
  search_backend: "searxng"
  extract_backend: "firecrawl"

# Or: SearXNG as the sole backend (web_extract will use the next available)
web:
  backend: "searxng"
```

SearXNG is search-only — it does not implement WebExtractProvider.  Users
who only configure SEARXNG_URL get web_search available; web_extract falls
back to the next available extract provider (or is unavailable if none).

Closes #19198 (Phase 2 Task 4 — SearXNG provider)
Ref: #11562 (original SearXNG PR)

hermes_cli/config.py

@@ -1832,6 +1832,14 @@ OPTIONAL_ENV_VARS = {
         "password": True,
         "category": "tool",
     },
+    "SEARXNG_URL": {
+        "description": "URL of your SearXNG instance for free self-hosted web search",
+        "prompt": "SearXNG URL (e.g. http://localhost:8080)",
+        "url": "https://searxng.github.io/searxng/",
+        "tools": ["web_search"],
+        "password": False,
+        "category": "tool",
+    },
     "BROWSERBASE_API_KEY": {
         "description": "Browserbase API key for cloud browser (optional — local browser works without this)",
         "prompt": "Browserbase API key",

hermes_cli/nous_subscription.py

@@ -255,6 +255,10 @@ def get_nous_subscription_features(
     terminal_cfg = config.get("terminal") if isinstance(config.get("terminal"), dict) else {}
 
     web_backend = str(web_cfg.get("backend") or "").strip().lower()
+    # Per-capability overrides: if set, they determine which backend is active for
+    # search/extract independently of web.backend.
+    web_search_backend = str(web_cfg.get("search_backend") or "").strip().lower()
+    web_extract_backend = str(web_cfg.get("extract_backend") or "").strip().lower()
     tts_provider = str(tts_cfg.get("provider") or "edge").strip().lower()
     browser_provider_explicit = "cloud_provider" in browser_cfg
     browser_provider = normalize_browser_cloud_provider(
@@ -280,6 +284,7 @@ def get_nous_subscription_features(
     direct_firecrawl = bool(get_env_value("FIRECRAWL_API_KEY") or get_env_value("FIRECRAWL_API_URL"))
     direct_parallel = bool(get_env_value("PARALLEL_API_KEY"))
     direct_tavily = bool(get_env_value("TAVILY_API_KEY"))
+    direct_searxng = bool(get_env_value("SEARXNG_URL"))
     direct_fal = fal_key_is_configured()
     direct_openai_tts = bool(resolve_openai_audio_api_key())
     direct_elevenlabs = bool(get_env_value("ELEVENLABS_API_KEY"))
@@ -323,10 +328,18 @@ def get_nous_subscription_features(
             or (web_backend == "firecrawl" and direct_firecrawl)
             or (web_backend == "parallel" and direct_parallel)
             or (web_backend == "tavily" and direct_tavily)
+            or (web_backend == "searxng" and direct_searxng)
+            # Per-capability overrides: search_backend or extract_backend may be set
+            # without web.backend (using the new split config from #20061)
+            or (web_search_backend == "searxng" and direct_searxng)
+            or (web_search_backend == "exa" and direct_exa)
+            or (web_search_backend == "firecrawl" and direct_firecrawl)
+            or (web_search_backend == "parallel" and direct_parallel)
+            or (web_search_backend == "tavily" and direct_tavily)
         )
     )
     web_available = bool(
-        managed_web_available or direct_exa or direct_firecrawl or direct_parallel or direct_tavily
+        managed_web_available or direct_exa or direct_firecrawl or direct_parallel or direct_tavily or direct_searxng
     )
 
     image_managed = image_tool_enabled and managed_image_available and not direct_fal
@@ -412,8 +425,8 @@ def get_nous_subscription_features(
             managed_by_nous=web_managed,
             direct_override=web_active and not web_managed,
             toolset_enabled=web_tool_enabled,
-            current_provider=web_backend or "",
+            current_provider=web_backend or web_search_backend or "",
-            explicit_configured=bool(web_backend),
+            explicit_configured=bool(web_backend or web_search_backend),
         ),
         "image_gen": NousFeatureState(
             key="image_gen",

hermes_cli/setup.py

@@ -394,7 +394,7 @@ def _print_setup_summary(config: dict, hermes_home):
             label = f"Web Search & Extract ({subscription_features.web.current_provider})"
         tool_status.append((label, True, None))
     else:
-        tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, or TAVILY_API_KEY"))
+        tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, TAVILY_API_KEY, or SEARXNG_URL"))
 
     # Browser tools (local Chromium, Camofox, Browserbase, Browser Use, or Firecrawl)
     browser_provider = subscription_features.browser.current_provider

hermes_cli/tools_config.py

@@ -299,6 +299,15 @@ TOOL_CATEGORIES = {
                     {"key": "FIRECRAWL_API_URL", "prompt": "Your Firecrawl instance URL (e.g., http://localhost:3002)"},
                 ],
             },
+            {
+                "name": "SearXNG",
+                "badge": "free · self-hosted · search only",
+                "tag": "Privacy-respecting metasearch engine — search only (pair with any extract provider)",
+                "web_backend": "searxng",
+                "env_vars": [
+                    {"key": "SEARXNG_URL", "prompt": "Your SearXNG instance URL (e.g., http://localhost:8080)", "url": "https://searxng.github.io/searxng/"},
+                ],
+            },
         ],
     },
     "image_gen": {

tests/tools/test_web_providers_searxng.py

@@ -0,0 +1,337 @@
+"""Tests for the SearXNG web search provider.
+
+Covers:
+- SearXNGSearchProvider.is_configured() env var gating
+- SearXNGSearchProvider.search() — happy path, HTTP error, request error, bad JSON
+- Result normalization (title, url, description, position)
+- Score-based sorting and limit truncation
+- _is_backend_available("searxng") integration
+- _get_backend() recognizes "searxng" as a valid configured backend
+- check_web_api_key() includes searxng in availability check
+"""
+from __future__ import annotations
+
+import json
+import os
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# SearXNGSearchProvider unit tests
+# ---------------------------------------------------------------------------
+
+
+class TestSearXNGSearchProviderIsConfigured:
+    def test_configured_when_url_set(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        assert SearXNGSearchProvider().is_configured() is True
+
+    def test_not_configured_when_url_missing(self, monkeypatch):
+        monkeypatch.delenv("SEARXNG_URL", raising=False)
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        assert SearXNGSearchProvider().is_configured() is False
+
+    def test_not_configured_when_url_empty_string(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "   ")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        assert SearXNGSearchProvider().is_configured() is False
+
+    def test_provider_name(self):
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        assert SearXNGSearchProvider().provider_name() == "searxng"
+
+    def test_implements_web_search_provider(self):
+        from tools.web_providers.base import WebSearchProvider
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        assert issubclass(SearXNGSearchProvider, WebSearchProvider)
+
+
+class TestSearXNGSearchProviderSearch:
+    """Happy path and error handling for SearXNGSearchProvider.search()."""
+
+    _SAMPLE_RESPONSE = {
+        "results": [
+            {"title": "Result A", "url": "https://a.example.com", "content": "Desc A", "score": 0.9},
+            {"title": "Result B", "url": "https://b.example.com", "content": "Desc B", "score": 0.7},
+            {"title": "Result C", "url": "https://c.example.com", "content": "Desc C", "score": 0.5},
+        ]
+    }
+
+    def _make_mock_response(self, json_data, status_code=200):
+        mock_resp = MagicMock()
+        mock_resp.status_code = status_code
+        mock_resp.json.return_value = json_data
+        mock_resp.raise_for_status = MagicMock()
+        return mock_resp
+
+    def test_happy_path_returns_normalized_results(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("test query", limit=5)
+
+        assert result["success"] is True
+        web = result["data"]["web"]
+        assert len(web) == 3
+        assert web[0]["title"] == "Result A"
+        assert web[0]["url"] == "https://a.example.com"
+        assert web[0]["description"] == "Desc A"
+        assert web[0]["position"] == 1
+
+    def test_results_sorted_by_score_descending(self, monkeypatch):
+        """Results should be sorted by score before limit is applied."""
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        unordered = {
+            "results": [
+                {"title": "Low",  "url": "https://low.example.com",  "content": "", "score": 0.1},
+                {"title": "High", "url": "https://high.example.com", "content": "", "score": 0.99},
+                {"title": "Mid",  "url": "https://mid.example.com",  "content": "", "score": 0.5},
+            ]
+        }
+        mock_resp = self._make_mock_response(unordered)
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("query", limit=5)
+
+        assert result["success"] is True
+        assert result["data"]["web"][0]["title"] == "High"
+        assert result["data"]["web"][1]["title"] == "Mid"
+        assert result["data"]["web"][2]["title"] == "Low"
+
+    def test_limit_is_respected(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("query", limit=2)
+
+        assert result["success"] is True
+        assert len(result["data"]["web"]) == 2
+
+    def test_position_is_one_indexed(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        mock_resp = self._make_mock_response(self._SAMPLE_RESPONSE)
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("query", limit=5)
+
+        positions = [r["position"] for r in result["data"]["web"]]
+        assert positions == [1, 2, 3]
+
+    def test_empty_results(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        mock_resp = self._make_mock_response({"results": []})
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("nothing", limit=5)
+
+        assert result["success"] is True
+        assert result["data"]["web"] == []
+
+    def test_missing_score_falls_back_to_zero(self, monkeypatch):
+        """Results without a score field should sort to the bottom."""
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        data = {
+            "results": [
+                {"title": "No score", "url": "https://noscore.example.com", "content": ""},
+                {"title": "Has score", "url": "https://scored.example.com", "content": "", "score": 0.8},
+            ]
+        }
+        mock_resp = self._make_mock_response(data)
+
+        with patch("httpx.get", return_value=mock_resp):
+            result = SearXNGSearchProvider().search("query", limit=5)
+
+        assert result["success"] is True
+        # Has score should sort first (0.8 > 0)
+        assert result["data"]["web"][0]["title"] == "Has score"
+
+    def test_http_error_returns_failure(self, monkeypatch):
+        import httpx
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+
+        mock_resp = MagicMock()
+        mock_resp.status_code = 500
+        http_err = httpx.HTTPStatusError("500", request=MagicMock(), response=mock_resp)
+
+        with patch("httpx.get", side_effect=http_err):
+            result = SearXNGSearchProvider().search("query", limit=5)
+
+        assert result["success"] is False
+        assert "500" in result["error"]
+
+    def test_request_error_returns_failure(self, monkeypatch):
+        import httpx
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+
+        with patch("httpx.get", side_effect=httpx.RequestError("connection refused")):
+            result = SearXNGSearchProvider().search("query", limit=5)
+
+        assert result["success"] is False
+        assert "localhost:8080" in result["error"] or "connection" in result["error"].lower()
+
+    def test_missing_url_returns_failure(self, monkeypatch):
+        monkeypatch.delenv("SEARXNG_URL", raising=False)
+        from tools.web_providers.searxng import SearXNGSearchProvider
+
+        result = SearXNGSearchProvider().search("query", limit=5)
+        assert result["success"] is False
+        assert "SEARXNG_URL" in result["error"]
+
+    def test_trailing_slash_stripped_from_url(self, monkeypatch):
+        """Base URL trailing slash should not produce double-slash in endpoint."""
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080/")
+        from tools.web_providers.searxng import SearXNGSearchProvider
+        mock_resp = self._make_mock_response({"results": []})
+
+        calls = []
+        def capture_get(url, **kwargs):
+            calls.append(url)
+            return mock_resp
+
+        with patch("httpx.get", side_effect=capture_get):
+            SearXNGSearchProvider().search("query", limit=5)
+
+        assert calls[0] == "http://localhost:8080/search", f"Got: {calls[0]}"
+
+
+# ---------------------------------------------------------------------------
+# Integration: _is_backend_available recognizes "searxng"
+# ---------------------------------------------------------------------------
+
+
+class TestIsBackendAvailable:
+    def test_searxng_available_when_url_set(self, monkeypatch):
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        from tools.web_tools import _is_backend_available
+        assert _is_backend_available("searxng") is True
+
+    def test_searxng_unavailable_when_url_missing(self, monkeypatch):
+        monkeypatch.delenv("SEARXNG_URL", raising=False)
+        from tools.web_tools import _is_backend_available
+        assert _is_backend_available("searxng") is False
+
+    def test_unknown_backend_still_false(self):
+        from tools.web_tools import _is_backend_available
+        assert _is_backend_available("unknownbackend") is False
+
+
+# ---------------------------------------------------------------------------
+# Integration: _get_backend() accepts "searxng" as configured value
+# ---------------------------------------------------------------------------
+
+
+class TestGetBackendSearXNG:
+    def test_configured_searxng_returns_searxng(self, monkeypatch):
+        from tools import web_tools
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "searxng"})
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        assert web_tools._get_backend() == "searxng"
+
+    def test_auto_detect_picks_searxng_when_only_url_set(self, monkeypatch):
+        """When no backend is configured but SEARXNG_URL is set, auto-detect returns it."""
+        from tools import web_tools
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {})
+        monkeypatch.delenv("FIRECRAWL_API_KEY", raising=False)
+        monkeypatch.delenv("FIRECRAWL_API_URL", raising=False)
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        monkeypatch.delenv("TAVILY_API_KEY", raising=False)
+        monkeypatch.delenv("EXA_API_KEY", raising=False)
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        # Suppress tool gateway
+        monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
+        assert web_tools._get_backend() == "searxng"
+
+    def test_searxng_does_not_override_higher_priority_provider(self, monkeypatch):
+        """Tavily (higher priority than searxng) should win in auto-detect."""
+        from tools import web_tools
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {})
+        monkeypatch.delenv("FIRECRAWL_API_KEY", raising=False)
+        monkeypatch.delenv("FIRECRAWL_API_URL", raising=False)
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        monkeypatch.setenv("TAVILY_API_KEY", "tvly-key")
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
+        assert web_tools._get_backend() == "tavily"
+
+
+# ---------------------------------------------------------------------------
+# Integration: check_web_api_key includes searxng
+# ---------------------------------------------------------------------------
+
+
+class TestCheckWebApiKey:
+    def test_searxng_satisfies_check_web_api_key(self, monkeypatch):
+        from tools import web_tools
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "searxng"})
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        assert web_tools.check_web_api_key() is True
+
+    def test_no_credentials_fails(self, monkeypatch):
+        from tools import web_tools
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {})
+        monkeypatch.delenv("FIRECRAWL_API_KEY", raising=False)
+        monkeypatch.delenv("FIRECRAWL_API_URL", raising=False)
+        monkeypatch.delenv("PARALLEL_API_KEY", raising=False)
+        monkeypatch.delenv("TAVILY_API_KEY", raising=False)
+        monkeypatch.delenv("EXA_API_KEY", raising=False)
+        monkeypatch.delenv("SEARXNG_URL", raising=False)
+        monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
+        monkeypatch.setattr(web_tools, "check_firecrawl_api_key", lambda: False)
+        assert web_tools.check_web_api_key() is False
+
+
+# ---------------------------------------------------------------------------
+# searxng-only: web_extract and web_crawl return clear errors
+# ---------------------------------------------------------------------------
+
+
+class TestSearXNGOnlyExtractCrawlErrors:
+    """When searxng is the active backend, extract/crawl must return clear errors."""
+
+    def test_web_crawl_searxng_returns_clear_error(self, monkeypatch):
+        import asyncio
+        from tools import web_tools
+
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "searxng"})
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
+        monkeypatch.setattr(web_tools, "check_firecrawl_api_key", lambda: False)
+        monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False, raising=False)
+
+        import json
+        result_str = asyncio.get_event_loop().run_until_complete(
+            web_tools.web_crawl_tool("https://example.com")
+        )
+        result = json.loads(result_str)
+        assert result["success"] is False
+        assert "search-only" in result["error"].lower() or "SearXNG" in result["error"]
+
+    def test_web_extract_searxng_returns_clear_error(self, monkeypatch):
+        import asyncio
+        from tools import web_tools
+
+        monkeypatch.setattr(web_tools, "_load_web_config", lambda: {"backend": "searxng"})
+        monkeypatch.setenv("SEARXNG_URL", "http://localhost:8080")
+        monkeypatch.setattr(web_tools, "_is_tool_gateway_ready", lambda: False)
+        monkeypatch.setattr("tools.interrupt.is_interrupted", lambda: False, raising=False)
+
+        import json
+        result_str = asyncio.get_event_loop().run_until_complete(
+            web_tools.web_extract_tool(["https://example.com"])
+        )
+        result = json.loads(result_str)
+        assert result["success"] is False
+        assert "search-only" in result["error"].lower() or "SearXNG" in result["error"]

tools/web_providers/searxng.py

@@ -0,0 +1,131 @@
+"""SearXNG web search provider.
+
+SearXNG is a free, self-hosted, privacy-respecting metasearch engine.
+It implements ``WebSearchProvider`` only — there is no extract capability.
+
+Configuration::
+
+    # ~/.hermes/config.yaml  (SEARXNG_URL is a URL, not a secret — use config.yaml not .env)
+    SEARXNG_URL: http://localhost:8080
+
+    # Use SearXNG for search, pair with any extract provider:
+    web:
+      search_backend: "searxng"
+      extract_backend: "firecrawl"
+
+Public SearXNG instances are listed at https://searx.space/ but self-hosting
+is recommended for production use (rate limits and availability vary per
+public instance).
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+from typing import Any, Dict
+
+from tools.web_providers.base import WebSearchProvider
+
+logger = logging.getLogger(__name__)
+
+
+class SearXNGSearchProvider(WebSearchProvider):
+    """Search via a SearXNG instance.
+
+    Requires ``SEARXNG_URL`` to be set (e.g. ``http://localhost:8080``).
+    No API key needed — SearXNG is open-source and self-hosted.
+
+    Uses the SearXNG JSON API (``/search?format=json``).  Results are
+    sorted by SearXNG's own score and truncated to *limit*.
+    """
+
+    def provider_name(self) -> str:
+        return "searxng"
+
+    def is_configured(self) -> bool:
+        """Return True when ``SEARXNG_URL`` is set to a non-empty value."""
+        return bool(os.getenv("SEARXNG_URL", "").strip())
+
+    def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
+        """Execute a search against the configured SearXNG instance.
+
+        Returns normalized results::
+
+            {
+                "success": True,
+                "data": {
+                    "web": [
+                        {
+                            "title": str,
+                            "url": str,
+                            "description": str,
+                            "position": int,
+                        },
+                        ...
+                    ]
+                }
+            }
+
+        On failure returns ``{"success": False, "error": str}``.
+        """
+        import httpx
+
+        base_url = os.getenv("SEARXNG_URL", "").strip().rstrip("/")
+        if not base_url:
+            return {"success": False, "error": "SEARXNG_URL is not set"}
+
+        params: Dict[str, Any] = {
+            "q": query,
+            "format": "json",
+            "pageno": 1,
+        }
+
+        try:
+            resp = httpx.get(
+                f"{base_url}/search",
+                params=params,
+                timeout=15,
+                headers={"Accept": "application/json"},
+            )
+            resp.raise_for_status()
+        except httpx.HTTPStatusError as exc:
+            logger.warning("SearXNG HTTP error: %s", exc)
+            return {"success": False, "error": f"SearXNG returned HTTP {exc.response.status_code}"}
+        except httpx.RequestError as exc:
+            logger.warning("SearXNG request error: %s", exc)
+            return {"success": False, "error": f"Could not reach SearXNG at {base_url}: {exc}"}
+
+        try:
+            data = resp.json()
+        except Exception as exc:  # noqa: BLE001
+            logger.warning("SearXNG response parse error: %s", exc)
+            return {"success": False, "error": "Could not parse SearXNG response as JSON"}
+
+        raw_results = data.get("results", [])
+
+        # SearXNG may return a score field; sort descending and cap to limit.
+        sorted_results = sorted(
+            raw_results,
+            key=lambda r: float(r.get("score", 0)),
+            reverse=True,
+        )[:limit]
+
+        web_results = [
+            {
+                "title": str(r.get("title", "")),
+                "url": str(r.get("url", "")),
+                "description": str(r.get("content", "")),
+                "position": i + 1,
+            }
+            for i, r in enumerate(sorted_results)
+        ]
+
+        logger.info(
+            "SearXNG search '%s': %d results (from %d raw, limit %d)",
+            query,
+            len(web_results),
+            len(raw_results),
+            limit,
+        )
+
+        return {"success": True, "data": {"web": web_results}}

tools/web_tools.py

@@ -126,7 +126,7 @@ def _get_backend() -> str:
     keys manually without running setup.
     """
     configured = (_load_web_config().get("backend") or "").lower().strip()
-    if configured in ("parallel", "firecrawl", "tavily", "exa"):
+    if configured in ("parallel", "firecrawl", "tavily", "exa", "searxng"):
         return configured
 
     # Fallback for manual / legacy config — pick the highest-priority
@@ -137,6 +137,7 @@ def _get_backend() -> str:
         ("parallel", _has_env("PARALLEL_API_KEY")),
         ("tavily", _has_env("TAVILY_API_KEY")),
         ("exa", _has_env("EXA_API_KEY")),
+        ("searxng", _has_env("SEARXNG_URL")),
     )
     for backend, available in backend_candidates:
         if available:
@@ -193,6 +194,8 @@ def _is_backend_available(backend: str) -> bool:
         return check_firecrawl_api_key()
     if backend == "tavily":
         return _has_env("TAVILY_API_KEY")
+    if backend == "searxng":
+        return _has_env("SEARXNG_URL")
     return False
 
 # ─── Firecrawl Client ────────────────────────────────────────────────────────
@@ -1187,6 +1190,16 @@ def web_search_tool(query: str, limit: int = 5) -> str:
             _debug.save()
             return result_json
 
+        if backend == "searxng":
+            from tools.web_providers.searxng import SearXNGSearchProvider
+            response_data = SearXNGSearchProvider().search(query, limit)
+            debug_call_data["results_count"] = len(response_data.get("data", {}).get("web", []))
+            result_json = json.dumps(response_data, indent=2, ensure_ascii=False)
+            debug_call_data["final_response_size"] = len(result_json)
+            _debug.log_call("web_search_tool", debug_call_data)
+            _debug.save()
+            return result_json
+
         if backend == "tavily":
             logger.info("Tavily search: '%s' (limit: %d)", query, limit)
             raw = _tavily_request("search", {
@@ -1337,6 +1350,13 @@ async def web_extract_tool(
                     "include_images": False,
                 })
                 results = _normalize_tavily_documents(raw, fallback_url=safe_urls[0] if safe_urls else "")
+            elif backend == "searxng":
+                # SearXNG is search-only — it cannot extract URL content
+                return json.dumps({
+                    "success": False,
+                    "error": "SearXNG is a search-only backend and cannot extract URL content. "
+                             "Set web.extract_backend to firecrawl, tavily, exa, or parallel.",
+                }, ensure_ascii=False)
             else:
                 # ── Firecrawl extraction ──
                 # Determine requested formats for Firecrawl v2
@@ -1712,6 +1732,14 @@ async def web_crawl_tool(
             _debug.save()
             return cleaned_result
 
+        # SearXNG is search-only — it cannot crawl
+        if backend == "searxng":
+            return json.dumps({
+                "error": "SearXNG is a search-only backend and cannot crawl URLs. "
+                         "Set FIRECRAWL_API_KEY for crawling, or use web_search instead.",
+                "success": False,
+            }, ensure_ascii=False)
+
         # web_crawl requires Firecrawl or the Firecrawl tool-gateway — Parallel has no crawl API
         if not check_firecrawl_api_key():
             return json.dumps({
@@ -2007,9 +2035,9 @@ def check_firecrawl_api_key() -> bool:
 def check_web_api_key() -> bool:
     """Check whether the configured web backend is available."""
     configured = _load_web_config().get("backend", "").lower().strip()
-    if configured in ("exa", "parallel", "firecrawl", "tavily"):
+    if configured in ("exa", "parallel", "firecrawl", "tavily", "searxng"):
         return _is_backend_available(configured)
-    return any(_is_backend_available(backend) for backend in ("exa", "parallel", "firecrawl", "tavily"))
+    return any(_is_backend_available(backend) for backend in ("exa", "parallel", "firecrawl", "tavily", "searxng"))
 
 
 def check_auxiliary_model() -> bool:
@@ -2044,6 +2072,8 @@ if __name__ == "__main__":
             print("   Using Parallel API (https://parallel.ai)")
         elif backend == "tavily":
             print("   Using Tavily API (https://tavily.com)")
+        elif backend == "searxng":
+            print(f"   Using SearXNG (search only): {os.getenv('SEARXNG_URL', '').strip()}")
         else:
             if firecrawl_url_available:
                 print(f"   Using self-hosted Firecrawl: {os.getenv('FIRECRAWL_API_URL').strip().rstrip('/')}")