feat(tools): add Firecrawl cloud browser provider (#5628)

* feat(tools): add Firecrawl cloud browser provider

Adds Firecrawl (https://firecrawl.dev) as a cloud browser provider
alongside Browserbase and Browser Use. All browser tools route through
Firecrawl's cloud browser via CDP when selected.

- tools/browser_providers/firecrawl.py — FirecrawlProvider
- tools/browser_tool.py — register in _PROVIDER_REGISTRY
- hermes_cli/tools_config.py — add to onboarding provider picker
- hermes_cli/setup.py — add to setup summary
- hermes_cli/config.py — add FIRECRAWL_BROWSER_TTL config
- website/docs/ — browser docs and env var reference

Based on #4490 by @developersdigest.

Co-Authored-By: Developers Digest <124798203+developersdigest@users.noreply.github.com>

* refactor: simplify FirecrawlProvider.emergency_cleanup

Use self._headers() and self._api_url() instead of duplicating
env-var reads and header construction.

* fix: recognize Firecrawl in subscription browser detection

_resolve_browser_feature_state() now handles "firecrawl" as a direct
browser provider (same pattern as "browser-use"), so hermes setup
summary correctly shows "Browser Automation (Firecrawl)" instead of
misreporting as "Local browser".

Also fixes test_config_version_unchanged assertion (11 → 12).

---------

Co-authored-by: Developers Digest <124798203+developersdigest@users.noreply.github.com>
This commit is contained in:
Siddharth Balyan 2026-04-06 14:05:26 -07:00 committed by GitHub
parent 150f70f821
commit 7b129636f0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 169 additions and 9 deletions

View file

@ -868,6 +868,13 @@ OPTIONAL_ENV_VARS = {
"password": True,
"category": "tool",
},
"FIRECRAWL_BROWSER_TTL": {
"description": "Firecrawl browser session TTL in seconds (optional, default 300)",
"prompt": "Browser session TTL (seconds)",
"tools": ["browser_navigate", "browser_click"],
"password": False,
"category": "tool",
},
"CAMOFOX_URL": {
"description": "Camofox browser server URL for local anti-detection browsing (e.g. http://localhost:9377)",
"prompt": "Camofox server URL",

View file

@ -131,6 +131,7 @@ def _browser_label(current_provider: str) -> str:
mapping = {
"browserbase": "Browserbase",
"browser-use": "Browser Use",
"firecrawl": "Firecrawl",
"camofox": "Camofox",
"local": "Local browser",
}
@ -156,6 +157,7 @@ def _resolve_browser_feature_state(
direct_camofox: bool,
direct_browserbase: bool,
direct_browser_use: bool,
direct_firecrawl: bool,
managed_browser_available: bool,
) -> tuple[str, bool, bool, bool]:
"""Resolve browser availability using the same precedence as runtime."""
@ -179,6 +181,10 @@ def _resolve_browser_feature_state(
available = bool(browser_local_available and direct_browser_use)
active = bool(browser_tool_enabled and available)
return current_provider, available, active, False
if current_provider == "firecrawl":
available = bool(browser_local_available and direct_firecrawl)
active = bool(browser_tool_enabled and available)
return current_provider, available, active, False
if current_provider == "camofox":
return current_provider, False, False, False
@ -315,6 +321,7 @@ def get_nous_subscription_features(
direct_camofox=direct_camofox,
direct_browserbase=direct_browserbase,
direct_browser_use=direct_browser_use,
direct_firecrawl=direct_firecrawl,
managed_browser_available=managed_browser_available,
)

View file

@ -657,7 +657,7 @@ def _print_setup_summary(config: dict, hermes_home):
else:
tool_status.append(("Web Search & Extract", False, "EXA_API_KEY, PARALLEL_API_KEY, FIRECRAWL_API_KEY/FIRECRAWL_API_URL, or TAVILY_API_KEY"))
# Browser tools (local Chromium, Camofox, Browserbase, or Browser Use)
# Browser tools (local Chromium, Camofox, Browserbase, Browser Use, or Firecrawl)
browser_provider = subscription_features.browser.current_provider
if subscription_features.browser.managed_by_nous:
tool_status.append(("Browser Automation (Nous Browserbase)", True, None))

View file

@ -315,6 +315,15 @@ TOOL_CATEGORIES = {
"browser_provider": "browser-use",
"post_setup": "browserbase",
},
{
"name": "Firecrawl",
"tag": "Cloud browser with remote execution",
"env_vars": [
{"key": "FIRECRAWL_API_KEY", "prompt": "Firecrawl API key", "url": "https://firecrawl.dev"},
],
"browser_provider": "firecrawl",
"post_setup": "browserbase",
},
{
"name": "Camofox",
"tag": "Local anti-detection browser (Firefox/Camoufox)",

View file

@ -63,4 +63,4 @@ class TestCamofoxConfigDefaults:
from hermes_cli.config import DEFAULT_CONFIG
# managed_persistence is auto-merged by _deep_merge, no version bump needed
assert DEFAULT_CONFIG["_config_version"] == 11
assert DEFAULT_CONFIG["_config_version"] == 12

View file

@ -0,0 +1,107 @@
"""Firecrawl cloud browser provider."""
import logging
import os
import uuid
from typing import Dict
import requests
from tools.browser_providers.base import CloudBrowserProvider
logger = logging.getLogger(__name__)
_BASE_URL = "https://api.firecrawl.dev"
class FirecrawlProvider(CloudBrowserProvider):
"""Firecrawl (https://firecrawl.dev) cloud browser backend."""
def provider_name(self) -> str:
return "Firecrawl"
def is_configured(self) -> bool:
return bool(os.environ.get("FIRECRAWL_API_KEY"))
# ------------------------------------------------------------------
# Session lifecycle
# ------------------------------------------------------------------
def _api_url(self) -> str:
return os.environ.get("FIRECRAWL_API_URL", _BASE_URL)
def _headers(self) -> Dict[str, str]:
api_key = os.environ.get("FIRECRAWL_API_KEY")
if not api_key:
raise ValueError(
"FIRECRAWL_API_KEY environment variable is required. "
"Get your key at https://firecrawl.dev"
)
return {
"Content-Type": "application/json",
"Authorization": f"Bearer {api_key}",
}
def create_session(self, task_id: str) -> Dict[str, object]:
ttl = int(os.environ.get("FIRECRAWL_BROWSER_TTL", "300"))
body: Dict[str, object] = {"ttl": ttl}
response = requests.post(
f"{self._api_url()}/v2/browser",
headers=self._headers(),
json=body,
timeout=30,
)
if not response.ok:
raise RuntimeError(
f"Failed to create Firecrawl browser session: "
f"{response.status_code} {response.text}"
)
data = response.json()
session_name = f"hermes_{task_id}_{uuid.uuid4().hex[:8]}"
logger.info("Created Firecrawl browser session %s", session_name)
return {
"session_name": session_name,
"bb_session_id": data["id"],
"cdp_url": data["cdpUrl"],
"features": {"firecrawl": True},
}
def close_session(self, session_id: str) -> bool:
try:
response = requests.delete(
f"{self._api_url()}/v2/browser/{session_id}",
headers=self._headers(),
timeout=10,
)
if response.status_code in (200, 201, 204):
logger.debug("Successfully closed Firecrawl session %s", session_id)
return True
else:
logger.warning(
"Failed to close Firecrawl session %s: HTTP %s - %s",
session_id,
response.status_code,
response.text[:200],
)
return False
except Exception as e:
logger.error("Exception closing Firecrawl session %s: %s", session_id, e)
return False
def emergency_cleanup(self, session_id: str) -> None:
try:
requests.delete(
f"{self._api_url()}/v2/browser/{session_id}",
headers=self._headers(),
timeout=5,
)
except ValueError:
logger.warning("Cannot emergency-cleanup Firecrawl session %s — missing credentials", session_id)
except Exception as e:
logger.debug("Emergency cleanup failed for Firecrawl session %s: %s", session_id, e)

View file

@ -79,6 +79,7 @@ except Exception:
from tools.browser_providers.base import CloudBrowserProvider
from tools.browser_providers.browserbase import BrowserbaseProvider
from tools.browser_providers.browser_use import BrowserUseProvider
from tools.browser_providers.firecrawl import FirecrawlProvider
from tools.tool_backend_helpers import normalize_browser_cloud_provider
# Camofox local anti-detection browser backend (optional).
@ -235,6 +236,7 @@ def _get_cdp_override() -> str:
_PROVIDER_REGISTRY: Dict[str, type] = {
"browserbase": BrowserbaseProvider,
"browser-use": BrowserUseProvider,
"firecrawl": FirecrawlProvider,
}
_cached_cloud_provider: Optional[CloudBrowserProvider] = None
@ -2036,12 +2038,12 @@ def check_browser_requirements() -> bool:
"""
Check if browser tool requirements are met.
In **local mode** (no Browserbase credentials): only the ``agent-browser``
CLI must be findable.
In **local mode** (no cloud provider configured): only the
``agent-browser`` CLI must be findable.
In **cloud mode** (Browserbase, Browser Use, or Firecrawl): the CLI
*and* the provider's required credentials must be present.
In **cloud mode** (BROWSERBASE_API_KEY set): the CLI *and* both
``BROWSERBASE_API_KEY`` / ``BROWSERBASE_PROJECT_ID`` must be present.
Returns:
True if all requirements are met, False otherwise
"""

View file

@ -77,13 +77,14 @@ For native Anthropic auth, Hermes prefers Claude Code's own credential files whe
| Variable | Description |
|----------|-------------|
| `PARALLEL_API_KEY` | AI-native web search ([parallel.ai](https://parallel.ai/)) |
| `FIRECRAWL_API_KEY` | Web scraping ([firecrawl.dev](https://firecrawl.dev/)) |
| `FIRECRAWL_API_KEY` | Web scraping and cloud browser ([firecrawl.dev](https://firecrawl.dev/)) |
| `FIRECRAWL_API_URL` | Custom Firecrawl API endpoint for self-hosted instances (optional) |
| `TAVILY_API_KEY` | Tavily API key for AI-native web search, extract, and crawl ([app.tavily.com](https://app.tavily.com/home)) |
| `EXA_API_KEY` | Exa API key for AI-native web search and contents ([exa.ai](https://exa.ai/)) |
| `BROWSERBASE_API_KEY` | Browser automation ([browserbase.com](https://browserbase.com/)) |
| `BROWSERBASE_PROJECT_ID` | Browserbase project ID |
| `BROWSER_USE_API_KEY` | Browser Use cloud browser API key ([browser-use.com](https://browser-use.com/)) |
| `FIRECRAWL_BROWSER_TTL` | Firecrawl browser session TTL in seconds (default: 300) |
| `BROWSER_CDP_URL` | Chrome DevTools Protocol URL for local browser (set via `/browser connect`, e.g. `ws://localhost:9222`) |
| `CAMOFOX_URL` | Camofox local anti-detection browser URL (default: `http://localhost:9377`) |
| `BROWSER_INACTIVITY_TIMEOUT` | Browser session inactivity timeout in seconds |

View file

@ -11,6 +11,7 @@ Hermes Agent includes a full browser automation toolset with multiple backend op
- **Browserbase cloud mode** via [Browserbase](https://browserbase.com) for managed cloud browsers and anti-bot tooling
- **Browser Use cloud mode** via [Browser Use](https://browser-use.com) as an alternative cloud browser provider
- **Firecrawl cloud mode** via [Firecrawl](https://firecrawl.dev) for cloud browsers with built-in scraping
- **Camofox local mode** via [Camofox](https://github.com/jo-inc/camofox-browser) for local anti-detection browsing (Firefox-based fingerprint spoofing)
- **Local Chrome via CDP** — connect browser tools to your own Chrome instance using `/browser connect`
- **Local browser mode** via the `agent-browser` CLI and a local Chromium installation
@ -23,7 +24,7 @@ Pages are represented as **accessibility trees** (text-based snapshots), making
Key capabilities:
- **Multi-provider cloud execution** — Browserbase or Browser Use, no local browser needed
- **Multi-provider cloud execution** — Browserbase, Browser Use, or Firecrawl — no local browser needed
- **Local Chrome integration** — attach to your running Chrome via CDP for hands-on browsing
- **Built-in stealth** — random fingerprints, CAPTCHA solving, residential proxies (Browserbase)
- **Session isolation** — each task gets its own browser session
@ -55,6 +56,32 @@ BROWSER_USE_API_KEY=***
Get your API key at [browser-use.com](https://browser-use.com). Browser Use provides a cloud browser via its REST API. If both Browserbase and Browser Use credentials are set, Browserbase takes priority.
### Firecrawl cloud mode
To use Firecrawl as your cloud browser provider, add:
```bash
# Add to ~/.hermes/.env
FIRECRAWL_API_KEY=fc-***
```
Get your API key at [firecrawl.dev](https://firecrawl.dev). Then select Firecrawl as your browser provider:
```bash
hermes setup tools
# → Browser Automation → Firecrawl
```
Optional settings:
```bash
# Self-hosted Firecrawl instance (default: https://api.firecrawl.dev)
FIRECRAWL_API_URL=http://localhost:3002
# Session TTL in seconds (default: 300)
FIRECRAWL_BROWSER_TTL=600
```
### Camofox local mode
[Camofox](https://github.com/jo-inc/camofox-browser) is a self-hosted Node.js server wrapping Camoufox (a Firefox fork with C++ fingerprint spoofing). It provides local anti-detection browsing without cloud dependencies.