The architecture has been updated

.env.example

@@ -1,326 +1,16 @@
-# Hermes Agent Environment Configuration
+OPENAI_BASE_URL=
-# Copy this file to .env and fill in your API keys
+OPENAI_API_KEY=
+MODEL_DEFAULT=
 
-# =============================================================================
+TERMINAL_DOCKER_IMAGE=python:3.12-slim
-# LLM PROVIDER (OpenRouter)
+TERMINAL_ENV=docker
-# =============================================================================
+HERMES_MAX_ITERATIONS=90
-# OpenRouter provides access to many models through one API
+HERMES_HOME=/app/hermes_data
-# All LLM calls go through OpenRouter - no direct provider keys needed
+HERMES_WORKSPACE_PATH=app/workspace
-# Get your key at: https://openrouter.ai/keys
-OPENROUTER_API_KEY=
 
-# Default model to use (OpenRouter format: provider/model)
+TELEGRAM_BOT_TOKEN=
-# Examples: anthropic/claude-opus-4.6, openai/gpt-4o, google/gemini-3-flash-preview, zhipuai/glm-4-plus
+TELEGRAM_ALLOWED_USERS=
-LLM_MODEL=anthropic/claude-opus-4.6
+TELEGRAM_HOME_CHANNEL=
-
-# =============================================================================
-# LLM PROVIDER (z.ai / GLM)
-# =============================================================================
-# z.ai provides access to ZhipuAI GLM models (GLM-4-Plus, etc.)
-# Get your key at: https://z.ai or https://open.bigmodel.cn
-GLM_API_KEY=
-# GLM_BASE_URL=https://api.z.ai/api/paas/v4  # Override default base URL
-
-# =============================================================================
-# LLM PROVIDER (Kimi / Moonshot)
-# =============================================================================
-# Kimi Code provides access to Moonshot AI coding models (kimi-k2.5, etc.)
-# Get your key at: https://platform.kimi.ai (Kimi Code console)
-# Keys prefixed sk-kimi- use the Kimi Code API (api.kimi.com) by default.
-# Legacy keys from platform.moonshot.ai need KIMI_BASE_URL override below.
-KIMI_API_KEY=
-# KIMI_BASE_URL=https://api.kimi.com/coding/v1  # Default for sk-kimi- keys
-# KIMI_BASE_URL=https://api.moonshot.ai/v1      # For legacy Moonshot keys
-# KIMI_BASE_URL=https://api.moonshot.cn/v1       # For Moonshot China keys
-
-# =============================================================================
-# LLM PROVIDER (MiniMax)
-# =============================================================================
-# MiniMax provides access to MiniMax models (global endpoint)
-# Get your key at: https://www.minimax.io
-MINIMAX_API_KEY=
-# MINIMAX_BASE_URL=https://api.minimax.io/v1  # Override default base URL
-
-# MiniMax China endpoint (for users in mainland China)
-MINIMAX_CN_API_KEY=
-# MINIMAX_CN_BASE_URL=https://api.minimaxi.com/v1  # Override default base URL
-
-# =============================================================================
-# LLM PROVIDER (OpenCode Zen)
-# =============================================================================
-# OpenCode Zen provides curated, tested models (GPT, Claude, Gemini, MiniMax, GLM, Kimi)
-# Pay-as-you-go pricing. Get your key at: https://opencode.ai/auth
-OPENCODE_ZEN_API_KEY=
-# OPENCODE_ZEN_BASE_URL=https://opencode.ai/zen/v1  # Override default base URL
-
-# =============================================================================
-# LLM PROVIDER (OpenCode Go)
-# =============================================================================
-# OpenCode Go provides access to open models (GLM-5, Kimi K2.5, MiniMax M2.5)
-# $10/month subscription. Get your key at: https://opencode.ai/auth
-OPENCODE_GO_API_KEY=
-# OPENCODE_GO_BASE_URL=https://opencode.ai/zen/go/v1  # Override default base URL
-
-# =============================================================================
-# TOOL API KEYS
-# =============================================================================
-
-# Parallel API Key - AI-native web search and extract
-# Get at: https://parallel.ai
-PARALLEL_API_KEY=
-
-# Firecrawl API Key - Web search, extract, and crawl
-# Get at: https://firecrawl.dev/
-FIRECRAWL_API_KEY=
-
-
-# FAL.ai API Key - Image generation
-# Get at: https://fal.ai/
-FAL_KEY=
-
-# Honcho - Cross-session AI-native user modeling (optional)
-# Builds a persistent understanding of the user across sessions and tools.
-# Get at: https://app.honcho.dev
-# Also requires ~/.honcho/config.json with enabled=true (see README).
-HONCHO_API_KEY=
-
-# =============================================================================
-# TERMINAL TOOL CONFIGURATION (mini-swe-agent backend)
-# =============================================================================
-# Backend type: "local", "singularity", "docker", "modal", or "ssh"
-# Terminal backend is configured in ~/.hermes/config.yaml (terminal.backend).
-# Use 'hermes setup' or 'hermes config set terminal.backend docker' to change.
-# Supported: local, docker, singularity, modal, ssh
-#
-# Only override here if you need to force a backend without touching config.yaml:
-# TERMINAL_ENV=local
-
-# Container images (for singularity/docker/modal backends)
-# TERMINAL_DOCKER_IMAGE=nikolaik/python-nodejs:python3.11-nodejs20
-# TERMINAL_SINGULARITY_IMAGE=docker://nikolaik/python-nodejs:python3.11-nodejs20
-TERMINAL_MODAL_IMAGE=nikolaik/python-nodejs:python3.11-nodejs20
-
-
-# Working directory for terminal commands
-# For local backend: "." means current directory (resolved automatically)
-# For remote backends (ssh/docker/modal/singularity): use an absolute path
-#   INSIDE the target environment, or leave unset for the backend's default
-#   (/root for modal, / for docker, ~ for ssh). Do NOT use a host-local path.
-# 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 (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 (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
-
-# =============================================================================
-# VOICE TRANSCRIPTION & OPENAI TTS
-# =============================================================================
-# Required for voice message transcription (Whisper) and OpenAI TTS voices.
-# Uses OpenAI's API directly (not via OpenRouter).
-# Named VOICE_TOOLS_OPENAI_KEY to avoid interference with OpenRouter.
-# Get at: https://platform.openai.com/api-keys
-VOICE_TOOLS_OPENAI_KEY=
-
-# =============================================================================
-# SLACK INTEGRATION
-# =============================================================================
-# Slack Bot Token - From Slack App settings (OAuth & Permissions)
-# Get at: https://api.slack.com/apps
-# SLACK_BOT_TOKEN=xoxb-...
-
-# Slack App Token - For Socket Mode (App-Level Tokens in Slack App settings)
-# SLACK_APP_TOKEN=xapp-...
-
-# Slack allowed users (comma-separated Slack user IDs)
-# SLACK_ALLOWED_USERS=
-
-# WhatsApp (built-in Baileys bridge — run `hermes whatsapp` to pair)
-# WHATSAPP_ENABLED=false
-# WHATSAPP_ALLOWED_USERS=15551234567
-
-# Email (IMAP/SMTP — send and receive emails as Hermes)
-# For Gmail: enable 2FA → create App Password at https://myaccount.google.com/apppasswords
-# EMAIL_ADDRESS=hermes@gmail.com
-# EMAIL_PASSWORD=xxxx xxxx xxxx xxxx
-# EMAIL_IMAP_HOST=imap.gmail.com
-# EMAIL_IMAP_PORT=993
-# EMAIL_SMTP_HOST=smtp.gmail.com
-# EMAIL_SMTP_PORT=587
-# EMAIL_POLL_INTERVAL=15
-# EMAIL_ALLOWED_USERS=your@email.com
-# EMAIL_HOME_ADDRESS=your@email.com
-
-# Gateway-wide: allow ALL users without an allowlist (default: false = deny)
-# Only set to true if you intentionally want open access.
-# GATEWAY_ALLOW_ALL_USERS=false
-
-# =============================================================================
-# RESPONSE PACING
-# =============================================================================
-# Human-like delays between message chunks on messaging platforms.
-# Makes the bot feel less robotic.
-# HERMES_HUMAN_DELAY_MODE=off     # off | natural | custom
-# HERMES_HUMAN_DELAY_MIN_MS=800   # Min delay in ms (custom mode)
-# HERMES_HUMAN_DELAY_MAX_MS=2500  # Max delay in ms (custom mode)
-
-# =============================================================================
-# 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 is configured in ~/.hermes/config.yaml under compression:
-# CONTEXT_COMPRESSION_ENABLED=true        # Enable auto-compression (default: true)
-# CONTEXT_COMPRESSION_THRESHOLD=0.85      # Compress at 85% of context limit
-# Model is set via compression.summary_model in config.yaml (default: google/gemini-3-flash-preview)
-
-# =============================================================================
-# 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
-
-# =============================================================================
-# SKILLS HUB (GitHub integration for skill search/install/publish)
-# =============================================================================
-
-# GitHub Personal Access Token — for higher API rate limits on skill search/install
-# Get at: https://github.com/settings/tokens (Fine-grained recommended)
-# GITHUB_TOKEN=ghp_xxxxxxxxxxxxxxxxxxxx
-
-# GitHub App credentials (optional — for bot identity on PRs)
-# GITHUB_APP_ID=
-# GITHUB_APP_PRIVATE_KEY_PATH=
-# GITHUB_APP_INSTALLATION_ID=
-
-# Groq API key (free tier — used for Whisper STT in voice mode)
-# GROQ_API_KEY=
-
-# =============================================================================
-# STT PROVIDER SELECTION
-# =============================================================================
-# Default STT provider is "local" (faster-whisper) — runs on your machine, no API key needed.
-# Install with: pip install faster-whisper
-# Model downloads automatically on first use (~150 MB for "base").
-# To use cloud providers instead, set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY above.
-# Provider priority: local > groq > openai
-# Configure in config.yaml: stt.provider: local | groq | openai
-
-# =============================================================================
-# STT ADVANCED OVERRIDES (optional)
-# =============================================================================
-# Override default STT models per provider (normally set via stt.model in config.yaml)
-# STT_GROQ_MODEL=whisper-large-v3-turbo
-# STT_OPENAI_MODEL=whisper-1
-
-# Override STT provider endpoints (for proxies or self-hosted instances)
-# GROQ_BASE_URL=https://api.groq.com/openai/v1
-# STT_OPENAI_BASE_URL=https://api.openai.com/v1
-
-HERMES_DATA_PATH=    # Укажите путь к папке .hermes
-HERMES_WORKSPACE_PATH=  # Укажите путь к воркспейсу гермеса
 
+BROWSER_URL=http://browser:9222
+BROWSER_VIEW_URL=

.gitignore

@@ -13,7 +13,10 @@ __pycache__/
 .env.test
 docker-compose.override.yml
 
-test_browser.py
+hermes_code/test_browser.py
+.git
+hermes_data
+workspace
 
 export*
 __pycache__/model_tools.cpython-310.pyc

browser_env/entrypoint.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 export DISPLAY=:99
 
 mkdir -p /var/run/dbus

config.example.yaml

@@ -0,0 +1,189 @@
+model:
+  default: qwen3.5-122b
+  provider: custom
+  base_url: https://llm.lambda.coredump.ru/v1
+toolsets:
+- all
+agent:
+  max_turns: 60
+  verbose: false
+  reasoning_effort: medium
+  personalities:
+    helpful: You are a helpful, friendly AI assistant.
+    technical: You are a technical expert. Provide detailed, accurate technical information.
+terminal:
+  backend: docker
+  cwd: .
+  timeout: 180
+  docker_image: python:3.12-slim
+  singularity_image: docker://python:3.12-slim
+  modal_image: python:3.12-slim
+  daytona_image: python:3.12-slim
+  container_cpu: 1.0
+  container_memory: 2048
+  container_disk: 15360
+  container_persistent: true
+  docker_volumes:
+  lifetime_seconds: 300
+browser:
+  inactivity_timeout: 120
+  record_sessions: false
+checkpoints:
+  enabled: false
+  max_snapshots: 50
+compression:
+  enabled: true
+  threshold: 0.8
+  summary_model: google/gemini-3-flash-preview
+  summary_provider: auto
+auxiliary:
+  vision:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  web_extract:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  compression:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  session_search:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  skills_hub:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  mcp:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+  flush_memories:
+    provider: auto
+    model: ''
+    base_url: ''
+    api_key: ''
+display:
+  compact: false
+  personality: helpful
+  resume_display: full
+  bell_on_complete: false
+  show_reasoning: false
+  skin: default
+  tool_progress: all
+  background_process_notifications: all
+tts:
+  provider: edge
+  edge:
+    voice: en-US-AriaNeural
+  elevenlabs:
+    voice_id: pNInz6obpgDQGcFmaJgB
+    model_id: eleven_multilingual_v2
+  openai:
+    model: gpt-4o-mini-tts
+    voice: alloy
+stt:
+  enabled: true
+  provider: local
+  local:
+    model: base
+  openai:
+    model: whisper-1
+  model: whisper-1
+voice:
+  record_key: ctrl+b
+  max_recording_seconds: 120
+  auto_tts: false
+  silence_threshold: 200
+  silence_duration: 3.0
+human_delay:
+  mode: 'off'
+  min_ms: 800
+  max_ms: 2500
+memory:
+  memory_enabled: true
+  user_profile_enabled: true
+  memory_char_limit: 2200
+  user_char_limit: 1375
+  nudge_interval: 10
+  flush_min_turns: 6
+delegation:
+  model: ''
+  provider: ''
+  base_url: ''
+  api_key: ''
+  max_iterations: 50
+  default_toolsets:
+  - terminal
+  - file
+  - web
+prefill_messages_file: ''
+honcho: {}
+timezone: ''
+discord:
+  require_mention: true
+  free_response_channels: ''
+  auto_thread: true
+command_allowlist: []
+quick_commands: {}
+personalities: {}
+security:
+  redact_secrets: true
+  tirith_enabled: true
+  tirith_path: tirith
+  tirith_timeout: 5
+  tirith_fail_open: true
+_config_version: 8
+session_reset:
+  mode: both
+  idle_minutes: 150
+  at_hour: 5
+skills:
+  creation_nudge_interval: 15
+platform_toolsets:
+  cli:
+  - hermes-cli
+  telegram:
+  - hermes-telegram
+  discord:
+  - hermes-discord
+  whatsapp:
+  - hermes-whatsapp
+  slack:
+  - hermes-slack
+  signal:
+  - hermes-signal
+  homeassistant:
+  - hermes-homeassistant
+code_execution:
+  timeout: 300
+  max_tool_calls: 50
+
+# ── Fallback Model ────────────────────────────────────────────────────
+# Automatic provider failover when primary is unavailable.
+# Uncomment and configure to enable. Triggers on rate limits (429),
+# overload (529), service errors (503), or connection failures.
+#
+# Supported providers:
+#   openrouter   (OPENROUTER_API_KEY)  — routes to any model
+#   openai-codex (OAuth — hermes login) — OpenAI Codex
+#   nous         (OAuth — hermes login) — Nous Portal
+#   zai          (ZAI_API_KEY)         — Z.AI / GLM
+#   kimi-coding  (KIMI_API_KEY)        — Kimi / Moonshot
+#   minimax      (MINIMAX_API_KEY)     — MiniMax
+#   minimax-cn   (MINIMAX_CN_API_KEY)  — MiniMax (China)
+#
+# For custom OpenAI-compatible endpoints, add base_url and api_key_env.
+#
+# fallback_model:
+#   provider: openrouter
+#   model: anthropic/claude-sonnet-4

docker-compose.yml

@@ -1,25 +1,19 @@
 services:
   agent:
-    build: .
+    build: 
+      context: ./hermes_code
+      dockerfile: Dockerfile
     container_name: hermes-brain
     env_file:
       - .env
-    volumes:
-      - .:/app/hermes_code:ro
-
-      - ${HERMES_DATA_PATH}/config.yaml:/app/hermes_data/config.yaml:ro
-      - ${HERMES_DATA_PATH}/SOUL.md:/app/hermes_data/SOUL.md:ro
-      - ./.env:/app/hermes_data/.env:ro
-
-      - ${HERMES_DATA_PATH}/state.db:/app/hermes_data/state.db:rw
-      - ${HERMES_DATA_PATH}/sessions:/app/hermes_data/sessions:rw
-      - ${HERMES_DATA_PATH}/logs:/app/hermes_data/logs:rw
-      - ${HERMES_DATA_PATH}/skills:/app/hermes_data/skills:rw
-      - ${HERMES_DATA_PATH}/sandboxes:/app/hermes_data/sandboxes:rw
-      - ${HERMES_DATA_PATH}/memories:/app/hermes_data/memories:rw
-      - ${HERMES_WORKSPACE_PATH}/hermes:/app/hermes_data/workspace:rw
     environment:
       - BROWSER_URL=http://browser:9222
+      - HERMES_HOME=/app/hermes_data
+    volumes:
+      - ./hermes_code:/app/hermes_code:ro
+      - ./hermes_data:/app/hermes_data:rw
+      - ./workspace:/app/workspace:rw
+      - ./config.example.yaml:/app/config.example.yaml:ro
     depends_on:
       - browser
     stdin_open: true
@@ -31,6 +25,14 @@ services:
       resources:
         limits:
           memory: 1.5G
+    command: >
+      bash -c "
+      if [ ! -f /app/hermes_data/config.yaml ]; then
+        echo 'Config not found, copying from example...';
+        cp /app/config.example.yaml /app/hermes_data/config.yaml;
+      fi;
+      exec python -m gateway.run
+      "
 
   browser:
     build:
@@ -59,13 +61,4 @@ volumes:
 
 networks:
   hermes-net:
-    driver: bridge      
+    driver: bridge
-
-          
-    # Optional: SSL configuration if needed
-    # extra_hosts:
-    #   - "host.docker.internal:host-gateway"
-
-# Uncomment the following if you need persistent logging or data
-# volumes:
-#   - ./logs:/tmp/logs

hermes_code/Dockerfile

@@ -20,5 +20,3 @@ RUN uv sync --frozen --no-install-project --extra tg
 COPY . .
 
 RUN uv sync --frozen --extra tg
-
-CMD ["python", "-m", "gateway.run"]