Prompt Assembly
Hermes deliberately separates: cached system prompt state ephemeral API call time additions This is one of the most important design choices in the project beca
Hermes deliberately separates: This is one of the most important design choices in the project because it affects: Primary files: The cached system prompt is assembled as three ordered tiers (see ): 1. stable — identity ( or fallback), tool/model guidance, skills prompt, environment hints, platform hints 2. …
What this page covers
- Cached system prompt layers
- Concrete example: assembled system prompt
- How SOUL.md appears in the prompt
- How context files are injected
- Context file discovery details
- API-call-time-only layers
- Memory snapshots
- Context files
- Skills index
- Supported prompt customization surfaces
- Use these surfaces first
- When to edit code instead
- Why prompt assembly is split this way
- Related docs
Section outline mirrored from the official Hermes Agent documentation. Follow any heading to read the complete text on the source site.
More in Developer Guide
Contributing
Thank you for contributing to Hermes Agent! This guide covers setting up your dev environment, understanding the codebase, and getting your PR merged. Contribut
Architecture
This page is the top level map of Hermes Agent internals. Use it to orient yourself in the codebase, then dive into subsystem specific docs for implementation d
Agent Loop Internals
The core orchestration engine is 's class — a large file that handles everything from prompt assembly to tool dispatch to provider failover. Core Responsibiliti
Context Compression and Caching
Context Compression and Caching Hermes Agent uses a dual compression system and Anthropic prompt caching to manage context window usage efficiently across long
Gateway Internals
The messaging gateway is the long running process that connects Hermes to 20+ external messaging platforms through a unified architecture. Key Files File Purpos
Session Storage
Session Storage Hermes Agent uses a SQLite database ( ) to persist session metadata, full message history, and model configuration across CLI and gateway sessio