Code Execution
Code Execution (Programmatic Tool Calling) The tool lets the agent write Python scripts that call Hermes tools programmatically, collapsing multi step workflows
The tool lets the agent write Python scripts that call Hermes tools programmatically, collapsing multi-step workflows into a single LLM turn. The script runs in a child process on the agent host, communicating with Hermes over a Unix domain socket RPC. 1. The agent writes a Python script using 2. Hermes generates a stub module with RPC functions 3. …
What this page covers
- How It Works
- When the Agent Uses This
- Practical Examples
- Data Processing Pipeline
- Multi-Step Web Research
- Bulk File Refactoring
- Build and Test Pipeline
- Execution Mode
- Resource Limits
- How Tool Calls Work Inside Scripts
- Error Handling
- Security
- Skill Environment Variable Passthrough
- HERMES variables in the child
- executecode vs terminal
- Platform Support
Section outline mirrored from the official Hermes Agent documentation. Follow any heading to read the complete text on the source site.
More in Core Features
Features Overview
Hermes Agent includes a rich set of capabilities that extend far beyond basic chat. From persistent memory and file aware context to browser automation and voic
Tools & Toolsets
Tools are functions that extend the agent's capabilities. They're organized into logical toolsets that can be enabled or disabled per platform. Available Tools
Skills System
Skills are on demand knowledge documents the agent can load when needed. They follow a progressive disclosure pattern to minimize token usage and are compatible
Curator
The curator is a background maintenance pass for agent created skills . It tracks how often each skill is viewed, used, and patched, moves long unused skills th
Persistent Memory
Hermes Agent has bounded, curated memory that persists across sessions. This lets it remember your preferences, your projects, your environment, and things it h
Memory Providers
Hermes Agent ships with 8 external memory provider plugins that give the agent persistent, cross session knowledge beyond the built in MEMORY.md and USER.md. On