Architecture

hermes-agent/
├── run_agent.py          # AIAgent class — core conversation loop
├── model_tools.py        # Tool orchestration, _discover_tools(), handle_function_call()
├── toolsets.py           # Toolset definitions, _HERMES_CORE_TOOLS list
├── cli.py                # HermesCLI class — interactive CLI orchestrator
├── hermes_state.py       # SessionDB — SQLite session store (FTS5 search)
├── agent/                # Agent internals
│   ├── prompt_builder.py     # System prompt assembly
│   ├── context_compressor.py # Auto context compression
│   ├── prompt_caching.py     # Anthropic prompt caching
│   ├── auxiliary_client.py   # Auxiliary LLM client (vision, summarization)
│   ├── model_metadata.py     # Model context lengths, token estimation
│   ├── display.py            # KawaiiSpinner, tool preview formatting
│   ├── skill_commands.py     # Skill slash commands (shared CLI/gateway)
│   └── trajectory.py         # Trajectory saving helpers
├── hermes_cli/           # CLI subcommands and setup
│   ├── main.py           # Entry point — all `hermes` subcommands
│   ├── config.py         # DEFAULT_CONFIG, OPTIONAL_ENV_VARS, migration
│   ├── commands.py       # Slash command definitions + SlashCommandCompleter
│   ├── callbacks.py      # Terminal callbacks (clarify, sudo, approval)
│   ├── setup.py          # Interactive setup wizard
│   ├── skin_engine.py    # Skin/theme engine — CLI visual customization
│   ├── skills_config.py  # `hermes skills` — enable/disable skills per platform
│   ├── tools_config.py   # `hermes tools` — enable/disable tools per platform
│   ├── skills_hub.py     # `/skills` slash command (search, browse, install)
│   ├── models.py         # Model catalog, provider model lists
│   └── auth.py           # Provider credential resolution
├── tools/                # Tool implementations (one file per tool)
│   ├── registry.py       # Central tool registry (schemas, handlers, dispatch)
│   ├── approval.py       # Dangerous command detection
│   ├── terminal_tool.py  # Terminal orchestration
│   ├── process_registry.py # Background process management
│   ├── file_tools.py     # File read/write/search/patch
│   ├── web_tools.py      # Web search/extract (Parallel + Firecrawl)
│   ├── browser_tool.py   # Browserbase browser automation
│   ├── code_execution_tool.py # execute_code sandbox
│   ├── delegate_tool.py  # Subagent delegation
│   ├── mcp_tool.py       # MCP client (~1050 lines)
│   └── environments/     # Terminal backends (local, docker, ssh, modal, daytona, singularity)
├── gateway/              # Messaging platform gateway
│   ├── run.py            # Main loop, slash commands, message dispatch
│   ├── session.py        # SessionStore — conversation persistence
│   └── platforms/        # Adapters: telegram, discord, slack, whatsapp, homeassistant, signal
├── acp_adapter/          # ACP server (VS Code / Zed / JetBrains integration)
├── cron/                 # Scheduler (jobs.py, scheduler.py)
├── environments/         # RL training environments (Atropos)
├── tests/                # Pytest suite (~3000 tests)
└── batch_runner.py       # Parallel batch processing

tools/registry.py  (no deps — imported by all tool files)
       ↑
tools/*.py  (each calls registry.register() at import time)
       ↑
model_tools.py  (imports tools/registry + triggers tool discovery)
       ↑
run_agent.py, cli.py, batch_runner.py, environments/

class AIAgent:
    def __init__(self,
        model: str = "anthropic/claude-opus-4.6",
        max_iterations: int = 90,
        enabled_toolsets: list = None,
        disabled_toolsets: list = None,
        quiet_mode: bool = False,
        save_trajectories: bool = False,
        platform: str = None,           # "cli", "telegram", etc.
        session_id: str = None,
        skip_context_files: bool = False,
        skip_memory: bool = False,
        # ... plus provider, api_mode, callbacks, routing params
    ): ...

    def chat(self, message: str) -> str:
        """Simple interface — returns final response string."""

    def run_conversation(self, user_message: str, system_message: str = None,
                         conversation_history: list = None, task_id: str = None) -> dict:
        """Full interface — returns dict with final_response + messages."""

while api_call_count < self.max_iterations and self.iteration_budget.remaining > 0:
    response = client.chat.completions.create(model=model, messages=messages, tools=tool_schemas)
    if response.tool_calls:
        for tool_call in response.tool_calls:
            result = handle_function_call(tool_call.name, tool_call.args, task_id)
            messages.append(tool_result_message(result))
        api_call_count += 1
    else:
        return response.content

# System message (built once per session)
{"role": "system", "content": "..."}

# User message
{"role": "user", "content": "..."}

# Assistant message (may include reasoning)
{"role": "assistant", "content": "...", "reasoning": "..."}

# Tool result message
{"role": "tool", "tool_call_id": "...", "content": "..."}

compression:
  enabled: true
  threshold: 0.50        # Compress at 50% of context limit
  summary_model: null    # Use same model as agent (or override)