Docs Explore Install Free
Hermes Agent Python NousResearch/hermes-agent

Hermes Agent Tours

6 tours available

Your First Contribution to Hermes Agent

beginner

Where to put new code in a 70-file Python agent with a learning loop, a messaging gateway, and a self-registering tool system

7 stops ~30 min
Prerequisites: Python 3.11+ and `uv` installed, Comfortable reading Python; you do not need to have written agent code before, Basic familiarity with `pytest`
onboardingcontributinggetting-started

The Self-Improving Skill System: How Hermes Builds and Refines Its Own Procedures

intermediate

How Hermes discovers, loads, preprocesses, invokes, and tracks its own skills across the full lifecycle

7 stops ~20 min
Prerequisites: Familiarity with Python type hints and `pathlib`, Basic understanding of YAML front matter (as used in Jekyll or similar), No prior Hermes knowledge required
skillsself-improvementprocedural-memory

Hermes Memory Architecture: How an Agent Remembers You Across Sessions

advanced

How a fact travels from a conversation into long-term storage and back into a future prompt

7 stops ~30 min
Prerequisites: Comfortable reading Python with type annotations, Basic understanding of abstract base classes (`ABC`) and the Template Method pattern, Familiarity with SQLite is helpful but not required
memorycuratorfts5honchocross-session

The Multi-Platform Gateway: One Agent, Six Chat Platforms, Shared Sessions

intermediate

How a Telegram message and a Discord DM share the same agent state inside Hermes

7 stops ~30 min
Prerequisites: Comfortable reading Python async code (you don't need to write it, just follow the `await` chain), Basic understanding of what a chat bot does: receives a message, generates a reply, sends it back, Familiarity with the concept of a session (stateful conversation) is helpful but not required
gatewayplatformsmulti-platformsession-managementpairing

Context Compression: Keeping Long Conversations Inside Token Budgets

intermediate

How Hermes detects context pressure, summarizes the middle of a conversation, and hands off to itself without losing the thread

7 stops ~30 min
Prerequisites: Familiar with the OpenAI message format (`role`, `content`, `tool_calls`, `tool_use`), Basic understanding of context windows and why token limits matter for LLMs, Python reading comfort; no need to run the code
contextcompressiontoken-budgetsummarization

Provider-Agnostic LLM Adapters: One Agent, Eight APIs

intermediate

How Hermes Agent normalizes OpenAI, Anthropic, Bedrock, Gemini, Codex Responses, and custom endpoints behind a single call interface

6 stops ~30 min
Prerequisites: Comfortable reading Python; no provider SDK knowledge required, Familiarity with what an LLM API call looks like (messages array, tools, max_tokens), Understanding that OpenAI's chat/completions format is the internal lingua franca Hermes normalizes from and to
llmprovidersabstractionmulti-provider
Your codebase next

Create code tours for your project

Intraview lets AI create interactive walkthroughs of any codebase. Install the free VS Code extension and generate your first tour in minutes.

Install Intraview Free