Hermes Agent

Hermes Agent is the layer that decides what to do; Ember is the engine that runs the model. Hermes handles channel routing (Telegram, Signal, WhatsApp), tool dispatch, memory and scheduling, and calls Ember as a custom OpenAI-compatible provider.

To wire it up, see Connect Hermes Agent. For where it sits in the wider system, see Architecture Overview.

Reasoning and routing

A single inference engine handles all reasoning tiers. The model is selected by prompt complexity and tool requirements:

Routing path:

User Message (Telegram)
    │
    ▼
Hermes Agent
    │  ┌── custom provider: http://127.0.0.1:8000/v1
    │  │   model: deepseek-v4-flash (ember-server)
    │  │   backend: ROCm 7.14 on AMD Radeon 8060S
    │  ▼
ember-server (Docker container, port 8000)
    │
    ├── FAST → single-turn response
    ├── DEFAULT → streaming chat completion
    ├── REASONING → high-temperature chain-of-thought
    └── COMPLEX → tool-calling agent loop with Hermes tool dispatch

The inference server runs as a Docker container with ROCm GPU passthrough (/dev/kfd, /dev/dri). The KV cache is disk-persisted — see Ember for the current deployment parameters.

Action: typed tools

Hermes Agent executes constrained operations through typed tools:

• Desktop/HID actions — JetKVM (WebRTC capture + USB HID) driven by Hermes computer-use tools
• Coordinate translation — vision model coordinates inverse-transformed to real screen coordinates before HID injection
• Code execution — sandboxed shell commands
• File operations — workspace read/write
• Messaging — post to Telegram topics, send alerts, create summaries
• Web & research — web search, page extraction
• Delegation — spawn sub-agents for parallel work

Memory

Hermes Agent provides three memory systems:

Hindsight (Long-Term Fact Storage)

Hindsight is the durable memory layer. It stores structured facts extracted from conversations and retrieves them on future turns via three parallel mechanisms:

• Semantic search — embedding-based similarity across all stored entries
• Keyword matching — full-text search over entity names and descriptions
• Entity graph traversal — follows relationships between entities (people, projects, systems) to surface connected facts

Three query modes:

Hindsight recall runs automatically (auto_recall), and the agent can also call hindsight_recall or hindsight_reflect explicitly when it needs long-term context. Writing is likewise automatic — auto_retain captures durable facts from conversations, and the retain tool is also called proactively when the agent learns a durable fact about the user, their environment, or a project.

Configuration:

Session Search (Conversation History)

FTS5-indexed archive of every past conversation session across all Hermes profiles. Accessed via session_search:

Session search is not automatically injected — it is called on demand when the user references past work.

Skills (Procedural Memory)

Reusable markdown files stored in ~/.hermes/skills/ that encode workflows for recurring task types. Each skill has a YAML frontmatter block (trigger conditions, description, category) and a markdown body with numbered steps, commands, and pitfalls. Skills are loaded explicitly via skill_view(name) and listed via skills_list().