mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-02 08:47:26 +08:00
36ea883d45
Merged main's latest changes including: - New hermes_cli/ unified CLI commands - File operations tools, fuzzy match, patch parser - RL training tools and tinker-atropos submodule - Enhanced batch_runner and run_agent - Gateway improvements (Telegram, Discord) - Cron job management - Installation scripts Preserved our branch-specific features: - Modal backend (atropos/backends/modal_backend.py) - Modal terminal tool integration (ModalProfile, _ModalSandboxPool, etc.) - Singularity/Apptainer support - Atropos AgentEnv Modal config fields - Combined pyproject.toml extras (atropos + messaging + cron + cli) Conflict resolution: - cli.py, model_tools.py, README.md: accepted main (newer features) - pyproject.toml: combined both extras and package lists - tools/terminal_tool.py: accepted main's base + re-inserted Modal integration
320 lines
13 KiB
Plaintext
320 lines
13 KiB
Plaintext
# Hermes Agent Environment Configuration
|
|
# Copy this file to .env and fill in your API keys
|
|
|
|
# =============================================================================
|
|
# CORE SETTINGS
|
|
# =============================================================================
|
|
# Agent backend:
|
|
# - openai : default Hermes-Agent loop (OpenAI function-calling via OpenAI SDK)
|
|
# - atropos : Atroposlib ServerManager/ManagedServer-backed loop (training/env integration)
|
|
HERMES_BACKEND=openai
|
|
|
|
|
|
# =============================================================================
|
|
# LOCAL / SELF-HOSTED OPENAI-COMPATIBLE ENDPOINTS (vLLM, SGLang, llama.cpp, etc.)
|
|
# =============================================================================
|
|
# For local development (matches the Atropos test env defaults):
|
|
# ATROPOS_SERVER_BASE_URL=http://127.0.0.1:8080
|
|
# ATROPOS_SERVER_MODEL=hermes-4-36b
|
|
# For hosted inference (Nous Research inference API):
|
|
ATROPOS_SERVER_BASE_URL=
|
|
ATROPOS_SERVER_MODEL=
|
|
ATROPOS_TOKENIZER_NAME=
|
|
# Set this to your Nous API key (Bearer token).
|
|
ATROPOS_SERVER_API_KEY=
|
|
|
|
# Debugging (prints to stdout; use with care)
|
|
# HERMES_DEBUG_ATROPOS_REQUEST=1
|
|
# HERMES_DEBUG_ATROPOS_RESPONSE=1
|
|
# HERMES_DEBUG_OPENAI_REQUEST=1
|
|
# HERMES_DEBUG_OPENAI_RESPONSE=1
|
|
|
|
# =============================================================================
|
|
# LOCAL / SELF-HOSTED OPENAI-COMPATIBLE ENDPOINTS (vLLM, SGLang, llama.cpp, etc.)
|
|
# =============================================================================
|
|
# If you set ATROPOS_SERVER_BASE_URL or OPENAI_BASE_URL, Hermes will use it instead
|
|
# of OpenRouter.
|
|
#
|
|
# Local server convenience (base URL without /v1):
|
|
# llama.cpp example (see `Hermes-Agent/scripts/launch_llama_cpp_hermes_4_36b.sh`):
|
|
# ATROPOS_SERVER_BASE_URL=http://127.0.0.1:8080
|
|
# ATROPOS_SERVER_MODEL=hermes-4-36b
|
|
# ATROPOS_TOKENIZER_NAME=NousResearch/Hermes-4.3-36B
|
|
# ATROPOS_SERVER_API_KEY=local
|
|
#
|
|
# Hosted Nous inference API:
|
|
# ATROPOS_SERVER_BASE_URL=https://inference-api.nousresearch.com
|
|
# ATROPOS_SERVER_MODEL=Hermes-4.3-36B
|
|
# ATROPOS_TOKENIZER_NAME=NousResearch/Hermes-4.3-36B
|
|
# ATROPOS_SERVER_API_KEY=sk-... (Bearer token)
|
|
#
|
|
# If you plan to run GRPO-style group sampling (e.g. `--env.group_size 4`) against
|
|
# llama.cpp, start the server with at least that many slots, e.g.:
|
|
# LLAMA_CPP_PARALLEL=4 Hermes-Agent/scripts/launch_llama_cpp_hermes_4_36b.sh
|
|
#
|
|
# Generic OpenAI-compatible (base URL should include /v1):
|
|
# OPENAI_BASE_URL=http://127.0.0.1:8080/v1
|
|
# OPENAI_API_KEY=local
|
|
|
|
# =============================================================================
|
|
# 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_BASE_URL=https://openrouter.ai/api/v1
|
|
OPENROUTER_API_KEY=
|
|
|
|
# Default model to use (OpenRouter format: provider/model)
|
|
# Examples: anthropic/claude-opus-4.6, openai/gpt-4o, google/gemini-2.0-flash, zhipuai/glm-4-plus
|
|
LLM_MODEL=anthropic/claude-opus-4.6
|
|
|
|
# =============================================================================
|
|
# 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", "modal", or "ssh"
|
|
# - local: Runs directly on your machine (fastest, no isolation)
|
|
# - ssh: Runs on remote server via SSH (great for sandboxing - agent can't touch its own code)
|
|
# - 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=local
|
|
|
|
|
|
# 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 for terminal commands
|
|
# For CLI: "." means current directory (resolved automatically from config.yaml)
|
|
# For containers (docker/singularity/modal): absolute path inside the container
|
|
# Usually managed by config.yaml (terminal.cwd) — uncomment to override
|
|
# TERMINAL_CWD=.
|
|
|
|
# Default command timeout in seconds
|
|
TERMINAL_TIMEOUT=60
|
|
|
|
# Cleanup inactive environments after this many seconds
|
|
TERMINAL_LIFETIME_SECONDS=300
|
|
|
|
# =============================================================================
|
|
# SSH REMOTE EXECUTION (for TERMINAL_ENV=ssh)
|
|
# =============================================================================
|
|
# Run terminal commands on a remote server via SSH.
|
|
# Agent code stays on your machine, commands execute remotely.
|
|
#
|
|
# SECURITY BENEFITS:
|
|
# - Agent cannot read your .env file (API keys protected)
|
|
# - Agent cannot modify its own code
|
|
# - Remote server acts as isolated sandbox
|
|
# - Can safely configure passwordless sudo on remote
|
|
#
|
|
# TERMINAL_SSH_HOST=192.168.1.100
|
|
# TERMINAL_SSH_USER=agent
|
|
# TERMINAL_SSH_PORT=22
|
|
# TERMINAL_SSH_KEY=~/.ssh/id_rsa
|
|
|
|
# =============================================================================
|
|
# SUDO SUPPORT (works with ALL terminal backends)
|
|
# =============================================================================
|
|
# If set, enables sudo commands by piping password via `sudo -S`.
|
|
# Works with: local, docker, singularity, modal, and ssh backends.
|
|
#
|
|
# SECURITY WARNING: Password stored in plaintext. Only use on trusted machines.
|
|
#
|
|
# ALTERNATIVES:
|
|
# - For SSH backend: Configure passwordless sudo on the remote server
|
|
# - For containers: Run as root inside the container (no sudo needed)
|
|
# - For local: Configure /etc/sudoers for specific commands
|
|
# - For CLI: Leave unset - you'll be prompted interactively with 45s timeout
|
|
#
|
|
# SUDO_PASSWORD=your_password_here
|
|
|
|
# =============================================================================
|
|
# MODAL CLOUD BACKEND (for TERMINAL_ENV=modal)
|
|
# =============================================================================
|
|
# Modal provides cloud sandboxes with per-second billing and auto-scaling.
|
|
# This implementation uses a warm pool of sandboxes for cost efficiency.
|
|
#
|
|
# SETUP:
|
|
# pip install modal && modal setup
|
|
# (Authenticates via browser, stores credentials locally)
|
|
#
|
|
# FEATURES:
|
|
# - Auto-scaling warm sandbox pool (no cold start after first use)
|
|
# - Named sandbox recovery (reconnects after restart)
|
|
# - Profile-based heterogeneous environments (CPU, GPU, different images)
|
|
# - Server-side idle_timeout protection against orphaned sandboxes
|
|
|
|
# Modal app name (groups all sandboxes, used for recovery)
|
|
TERMINAL_MODAL_APP_NAME=hermes-sandbox
|
|
|
|
# Default profile when none specified
|
|
TERMINAL_MODAL_DEFAULT_PROFILE=default
|
|
|
|
# Profile config file (optional - YAML format, see modal_profiles.yaml)
|
|
# TERMINAL_MODAL_PROFILES_FILE=modal_profiles.yaml
|
|
|
|
# --- Default Profile Settings (used if no YAML file) ---
|
|
# These apply when no profile is specified or for the "default" profile
|
|
TERMINAL_MODAL_IMAGE=python:3.11
|
|
TERMINAL_MODAL_MIN_POOL=1
|
|
TERMINAL_MODAL_MAX_POOL=5
|
|
TERMINAL_MODAL_IDLE_TIMEOUT=120
|
|
TERMINAL_MODAL_MAX_LIFETIME=3600
|
|
TERMINAL_MODAL_SCALE_DOWN_IDLE=180
|
|
|
|
# --- Custom Profile Example: pytorch-gpu ---
|
|
# Uncomment to enable a GPU profile for ML tasks
|
|
# Usage: terminal_tool("python train.py", profile="pytorch-gpu")
|
|
#
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_IMAGE=pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_GPU=T4
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_MEMORY=16384
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_MIN_POOL=0
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_MAX_POOL=2
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_IDLE_TIMEOUT=60
|
|
|
|
# --- Custom Profile Example: node ---
|
|
# Uncomment to enable a Node.js profile
|
|
# Usage: terminal_tool("npm test", profile="node")
|
|
#
|
|
# TERMINAL_MODAL_PROFILE_node_IMAGE=node:18
|
|
# TERMINAL_MODAL_PROFILE_node_MIN_POOL=0
|
|
# TERMINAL_MODAL_PROFILE_node_MAX_POOL=3
|
|
|
|
# =============================================================================
|
|
# MODAL SECRETS (Secure credential injection)
|
|
# =============================================================================
|
|
# Modal Secrets allow you to securely pass API keys, passwords, and other
|
|
# sensitive data to your sandboxes without exposing them in code or logs.
|
|
#
|
|
# SETUP SECRETS:
|
|
# 1. Via Dashboard: https://modal.com/secrets
|
|
# 2. Via CLI: modal secret create my-secret KEY1=value1 KEY2=value2
|
|
# 3. Via CLI with env: modal secret create my-secret API_KEY="$API_KEY"
|
|
#
|
|
# LIST SECRETS:
|
|
# modal secret list
|
|
#
|
|
# DELETE SECRETS:
|
|
# modal secret delete my-secret
|
|
|
|
# Global secrets applied to ALL profiles (comma-separated secret names)
|
|
# These secrets must be created on Modal dashboard or via CLI first
|
|
# TERMINAL_MODAL_SECRETS=my-api-keys,database-creds
|
|
|
|
# Per-profile secrets (comma-separated secret names)
|
|
# TERMINAL_MODAL_PROFILE_pytorch_gpu_SECRETS=huggingface-token,wandb-key
|
|
|
|
# Per-profile environment variables (semicolon-separated KEY=VALUE pairs)
|
|
# TERMINAL_MODAL_PROFILE_default_ENV_VARS=DEBUG=1;LOG_LEVEL=info
|
|
|
|
# Load local .env file into sandbox (useful for development)
|
|
# TERMINAL_MODAL_PROFILE_default_USE_DOTENV=true
|
|
|
|
# =============================================================================
|
|
# 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 (default: 300)
|
|
# Sessions are cleaned up after this duration of inactivity
|
|
BROWSER_SESSION_TIMEOUT=300
|
|
|
|
# Browser inactivity timeout - auto-cleanup inactive sessions (default: 120 = 2 min)
|
|
# Browser sessions are automatically closed after this period of no activity
|
|
BROWSER_INACTIVITY_TIMEOUT=120
|
|
|
|
# =============================================================================
|
|
# SESSION LOGGING
|
|
# =============================================================================
|
|
# Session trajectories are automatically saved to logs/ directory
|
|
# Format: logs/session_YYYYMMDD_HHMMSS_UUID.json
|
|
# Contains full conversation history in trajectory format for debugging/replay
|
|
|
|
# =============================================================================
|
|
# 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
|
|
|
|
# =============================================================================
|
|
# CONTEXT COMPRESSION (Auto-shrinks long conversations)
|
|
# =============================================================================
|
|
# When conversation approaches model's context limit, middle turns are
|
|
# automatically summarized to free up space.
|
|
#
|
|
# CONTEXT_COMPRESSION_ENABLED=true # Enable auto-compression (default: true)
|
|
# CONTEXT_COMPRESSION_THRESHOLD=0.85 # Compress at 85% of context limit
|
|
# CONTEXT_COMPRESSION_MODEL=google/gemini-2.0-flash-001 # Fast model for summaries
|
|
|
|
# =============================================================================
|
|
# RL TRAINING (Tinker + Atropos)
|
|
# =============================================================================
|
|
# Run reinforcement learning training on language models using the Tinker API.
|
|
# Requires the rl-server to be running (from tinker-atropos package).
|
|
|
|
# Tinker API Key - RL training service
|
|
# Get at: https://tinker-console.thinkingmachines.ai/keys
|
|
TINKER_API_KEY=
|
|
|
|
# Weights & Biases API Key - Experiment tracking and metrics
|
|
# Get at: https://wandb.ai/authorize
|
|
WANDB_API_KEY=
|
|
|
|
# RL API Server URL (default: http://localhost:8080)
|
|
# Change if running the rl-server on a different host/port
|
|
# RL_API_URL=http://localhost:8080
|