Academy → Practical guidesOfficial documentation · clear explanation

Using Hermes as a Python Library

Using Hermes as a Python Library

Developer12 minutes3 questions2026-08-09
The idea in one minute

Start with meaning, then move to detail.

This lesson explains Using Hermes as a Python Library as part of Hermes internals and extension points. You will learn what it does, when it matters, and the smallest safe test that proves it works.

If you are new

If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?

For hands-on use

For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.

For specialists

For advanced readers, inspect Installation, Basic Usage, Full Conversation Control, then verify failure modes and version compatibility.

What do you need first?

Know Python, Git, and basic project structure before changing code.

What will you know?

A clear outcome before you read.

  • Understand Using Hermes as a Python Library without assumed prior knowledge.
  • Separate the source description from what still needs testing in your environment.
  • Read the first command and identify its inputs and outputs before copying it.
Lesson terms

Short definitions before the details.

Tool
A structured action the agent can call to read or change something.
Official page description

Embed AIAgent in your own Python scripts, web apps, or automation pipelines — no CLI required

Topic map

What does the source say, and in what order?

  1. 01
    Installation

    Start here to understand the core idea or structure.

  2. 02
    Basic Usage

    Read this after the foundation, then connect it to the previous step.

  3. 03
    Full Conversation Control

    Read this after the foundation, then connect it to the previous step.

  4. 04
    Configuring Tools

    Read this after the foundation, then connect it to the previous step.

  5. 05
    Multi-turn Conversations

    Read this after the foundation, then connect it to the previous step.

  6. 06
    Saving Trajectories

    Read this after the foundation, then connect it to the previous step.

  7. 07
    Custom System Prompts

    Read this after the foundation, then connect it to the previous step.

  8. 08
    Batch Processing

    Read this after the foundation, then connect it to the previous step.

  9. 09
    Integration Examples

    Read this after the foundation, then connect it to the previous step.

  10. 10
    FastAPI Endpoint

    Finish here to verify the result and special cases.

Examples from the official page

Copy only after you understand the effect.

git clone https://github.com/NousResearch/hermes-agent.git cd hermes-agent uv sync
`chat()` handles the full conversation loop internally — tool calls, retries, everything — and returns just the final text response. :::warning Always set `quiet_mode=True` when embedding Hermes in your own code. Without it, the agent prints CLI spinners, progress indicators, and other terminal output that will clutter your application's output. ::: --- ## Full Conversation Control For more control over the conversation, use `run_conversation()` directly. It returns a dictionary with the full response, message history, and metadata:
The returned dictionary contains: - **`final_response`** — The agent's final text reply - **`messages`** — The complete message history (system, user, assistant, tool calls) (The `task_id` you pass in is stored on the agent instance for VM isolation but isn't echoed back in the return dict.) You can also pass a custom system message that overrides the ephemeral system prompt for that call:
Try it now

Read the first command and identify its inputs and outputs before copying it.

Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.

Knowledge check

Three decisions before completion.

1. What is the source of truth when “Using Hermes as a Python Library” changes?
2. What is the best way to apply this lesson?
3. What should happen before a step can modify files or an external account?