248acf715e
- Introduced new browser automation tools in `browser_tool.py` for navigating, interacting with, and extracting content from web pages using the agent-browser CLI and Browserbase cloud execution. - Updated `.env.example` to include new configuration options for Browserbase API keys and session settings. - Enhanced `model_tools.py` and `toolsets.py` to integrate browser tools into the existing tool framework, ensuring consistent access across toolsets. - Updated `README.md` with setup instructions for browser tools and their usage examples. - Added new test script `test_modal_terminal.py` to validate Modal terminal backend functionality. - Improved `run_agent.py` to support browser tool integration and logging enhancements for better tracking of API responses.
159 lines
6.3 KiB
Plaintext
159 lines
6.3 KiB
Plaintext
# Hermes Agent Environment Configuration
|
|
# Copy this file to .env and fill in your API keys
|
|
|
|
# =============================================================================
|
|
# LLM PROVIDER (OpenRouter)
|
|
# =============================================================================
|
|
# OpenRouter provides access to many models through one API
|
|
# All LLM calls go through OpenRouter - no direct provider keys needed
|
|
# Get your key at: https://openrouter.ai/keys
|
|
OPENROUTER_API_KEY=
|
|
|
|
# Default model to use (OpenRouter format: provider/model)
|
|
# Examples: anthropic/claude-sonnet-4, openai/gpt-4o, google/gemini-2.0-flash, zhipuai/glm-4-plus
|
|
LLM_MODEL=anthropic/claude-sonnet-4
|
|
|
|
# =============================================================================
|
|
# TOOL API KEYS
|
|
# =============================================================================
|
|
|
|
# Firecrawl API Key - Web search, extract, and crawl
|
|
# Get at: https://firecrawl.dev/
|
|
FIRECRAWL_API_KEY=
|
|
|
|
# Nous Research API Key - Vision analysis and multi-model reasoning
|
|
# Get at: https://inference-api.nousresearch.com/
|
|
NOUS_API_KEY=
|
|
|
|
# FAL.ai API Key - Image generation
|
|
# Get at: https://fal.ai/
|
|
FAL_KEY=
|
|
|
|
# =============================================================================
|
|
# TERMINAL TOOL CONFIGURATION (mini-swe-agent backend)
|
|
# =============================================================================
|
|
# Backend type: "local", "singularity", "docker", or "modal"
|
|
# - local: Runs directly on your machine (fastest, no isolation)
|
|
# - singularity: Runs in Apptainer/Singularity containers (HPC clusters, no root needed)
|
|
# - docker: Runs in Docker containers (isolated, requires Docker + docker group)
|
|
# - modal: Runs in Modal cloud sandboxes (scalable, requires Modal account)
|
|
TERMINAL_ENV=singularity
|
|
|
|
# Container images (for singularity/docker/modal backends)
|
|
TERMINAL_DOCKER_IMAGE=python:3.11
|
|
TERMINAL_SINGULARITY_IMAGE=docker://python:3.11
|
|
TERMINAL_MODAL_IMAGE=python:3.11
|
|
|
|
# Working directory inside the container
|
|
TERMINAL_CWD=/tmp
|
|
|
|
# Default command timeout in seconds
|
|
TERMINAL_TIMEOUT=60
|
|
|
|
# Cleanup inactive environments after this many seconds
|
|
TERMINAL_LIFETIME_SECONDS=300
|
|
|
|
# =============================================================================
|
|
# MODAL CLOUD BACKEND (Optional - for TERMINAL_ENV=modal)
|
|
# =============================================================================
|
|
# Modal uses CLI authentication, not environment variables.
|
|
# Run: pip install modal && modal setup
|
|
# This will authenticate via browser and store credentials locally.
|
|
# No API key needed in .env - Modal handles auth automatically.
|
|
|
|
# =============================================================================
|
|
# BROWSER TOOL CONFIGURATION (agent-browser + Browserbase)
|
|
# =============================================================================
|
|
# Browser automation requires Browserbase cloud service for remote browser execution.
|
|
# This allows the agent to navigate websites, fill forms, and extract information.
|
|
#
|
|
# STEALTH MODES:
|
|
# - Basic Stealth: ALWAYS active (random fingerprints, auto CAPTCHA solving)
|
|
# - Advanced Stealth: Requires BROWSERBASE_ADVANCED_STEALTH=true (Scale Plan only)
|
|
|
|
# Browserbase API Key - Cloud browser execution
|
|
# Get at: https://browserbase.com/
|
|
BROWSERBASE_API_KEY=
|
|
|
|
# Browserbase Project ID - From your Browserbase dashboard
|
|
BROWSERBASE_PROJECT_ID=
|
|
|
|
# Enable residential proxies for better CAPTCHA solving (default: true)
|
|
# Routes traffic through residential IPs, significantly improves success rate
|
|
BROWSERBASE_PROXIES=true
|
|
|
|
# Enable advanced stealth mode (default: false, requires Scale Plan)
|
|
# Uses custom Chromium build to avoid bot detection altogether
|
|
BROWSERBASE_ADVANCED_STEALTH=false
|
|
|
|
# Browser session timeout in seconds (optional, default: 300)
|
|
# Sessions are cleaned up after this duration of inactivity
|
|
BROWSER_SESSION_TIMEOUT=300
|
|
|
|
# =============================================================================
|
|
# Browser automation requires Browserbase cloud service for remote browser execution.
|
|
# This allows the agent to navigate websites, fill forms, and extract information.
|
|
|
|
# Browserbase API Key - Cloud browser execution
|
|
# Get at: https://browserbase.com/
|
|
BROWSERBASE_API_KEY=
|
|
|
|
# Browserbase Project ID - From your Browserbase dashboard
|
|
BROWSERBASE_PROJECT_ID=
|
|
|
|
# Enable proxies for better CAPTCHA solving and anti-bot avoidance (default: true)
|
|
# Proxies route traffic through residential IPs for more reliable access
|
|
BROWSERBASE_PROXIES=true
|
|
|
|
# Enable advanced stealth mode (default: false, requires Scale Plan)
|
|
# Uses custom Chromium build to avoid bot detection altogether
|
|
BROWSERBASE_ADVANCED_STEALTH=false
|
|
|
|
# Browser session timeout in seconds (optional, default: 300)
|
|
# Sessions are cleaned up after this duration of inactivity
|
|
BROWSER_SESSION_TIMEOUT=300
|
|
|
|
# =============================================================================
|
|
# Browser automation requires Browserbase cloud service for remote browser execution.
|
|
# This allows the agent to navigate websites, fill forms, and extract information.
|
|
|
|
# Browserbase API Key - Cloud browser execution
|
|
# Get at: https://browserbase.com/
|
|
BROWSERBASE_API_KEY=
|
|
|
|
# Browserbase Project ID - From your Browserbase dashboard
|
|
BROWSERBASE_PROJECT_ID=
|
|
|
|
# Browser session timeout in seconds (optional, default: 300)
|
|
# Sessions are cleaned up after this duration of inactivity
|
|
BROWSER_SESSION_TIMEOUT=300
|
|
|
|
# =============================================================================
|
|
# LEGACY/OPTIONAL API KEYS
|
|
# =============================================================================
|
|
|
|
# Morph API Key - For legacy Hecate terminal backend (terminal-hecate tool)
|
|
# Get at: https://morph.so/
|
|
MORPH_API_KEY=
|
|
|
|
# Hecate VM Settings (only if using terminal-hecate tool)
|
|
HECATE_VM_LIFETIME_SECONDS=300
|
|
HECATE_DEFAULT_SNAPSHOT_ID=snapshot_p5294qxt
|
|
|
|
# =============================================================================
|
|
# DEBUG OPTIONS
|
|
# =============================================================================
|
|
WEB_TOOLS_DEBUG=false
|
|
VISION_TOOLS_DEBUG=false
|
|
MOA_TOOLS_DEBUG=false
|
|
IMAGE_TOOLS_DEBUG=false
|
|
|
|
# Scratch directory for Singularity sandboxes (optional)
|
|
# If not set, uses /scratch (if available) or /tmp
|
|
# Set this to a directory with lots of space for large pip installs
|
|
# TERMINAL_SCRATCH_DIR=/scratch/myuser
|
|
|
|
# Disk usage warning threshold in GB (default: 500)
|
|
# Warning is printed when total sandbox disk usage exceeds this
|
|
TERMINAL_DISK_WARNING_GB=500
|