Hermes For Function Calling: Tool-Use Without OpenAI

Hermes ships with a documented function-calling format. That makes it one of the few open-weight models you can wire into agent frameworks without months of prompting hacks.

10 min · Reviewed 2026

Why function calling matters more than chat quality

For most production workloads, the model has to do something — call an API, query a database, write to a calendar. That is function calling. A model that handles it reliably is more valuable in agent stacks than one that writes prettier prose. Hermes was tuned with this in mind, and it shows.

What the Hermes format looks like

Hermes uses a tool-use grammar that the model card documents in detail. The exact tags vary by version, but the pattern is consistent: the system prompt declares the available tools as JSON schemas, the model emits a structured tool-call block, your harness executes it and returns results, and the model continues. This is the same shape OpenAI and Anthropic use — Hermes just exposes it for an open-weight model.

Pattern (illustrative, not exact tags): [SYSTEM] You have access to the following tools: search_inventory(query: string) -> list of items send_email(to: string, subject: string, body: string) [USER] Find us 5 size 10 hiking boots and email John the list. [MODEL] <tool_call> search_inventory({"query": "size 10 hiking boots"}) </tool_call> [HARNESS RETURNS] [ {sku: , name: }, ] [MODEL] <tool_call> send_email({"to": "john@", "subject": "Boots", "body": ""}) </tool_call>The dance is the same in any tool-using model. Hermes documents the exact grammar in its model card.

Where it shines

Building agents that should work without an OpenAI dependency.
Self-hosted assistants where the tool list is sensitive (internal databases, private endpoints).
Cost-sensitive agent workloads — Hermes 8B handles a lot of routine tool calls cheaply.
Latency-sensitive use cases on dedicated hardware — local inference avoids round-trip to a cloud API.

Where to be careful

Risk	What goes wrong	Mitigation
Schema drift	Model emits a slightly malformed tool call	Validate every call against the schema before executing
Hallucinated tool names	Model invents a tool you didn't declare	Allowlist tool names; refuse anything else
Argument hallucination	Model fills required fields with plausible-but-wrong values	Prompt to confirm before destructive actions
Multi-step planning	Model gets confused after 3-4 tool calls	Use a smaller plan-then-execute split or a larger model for planning

Applied exercise

Read the function-calling section of the Hermes model card for the version you run.
Implement a single tool — a fake 'lookup_user(id)' that returns canned data.
Wire Hermes to call it and verify the model emits the documented format.
Add a deliberately invalid tool call to your test set and confirm your harness rejects it gracefully.

The big idea: Hermes makes open-weight tool use practical. The work is in the harness — validate everything, allowlist always.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-hermes-function-calling-creators

What is the main idea of "Hermes For Function Calling: Tool-Use Without OpenAI"?
1. Hermes ships with a documented function-calling format.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Hermes For Function Calling: Tool-Use Without OpenAI"?
1. tool use
2. function calling
3. structured grammar
4. agent frameworks
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Building agents that should work without an OpenAI dependency.
4. Treat the AI output as automatically correct
What should a careful learner remember about "Validate, don't trust"?
1. Use "Validate, don't trust" as a reminder to verify the AI output before anyone relies on it.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about function calling be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about function calling.
Which action would help you apply "Hermes For Function Calling: Tool-Use Without OpenAI" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Self-hosted assistants where the tool list is sensitive (internal databases, private endpoints).

← Back to interactive lesson

Tendril · Creators · Model Families

Hermes For Function Calling: Tool-Use Without OpenAI

Hermes ships with a documented function-calling format. That makes it one of the few open-weight models you can wire into agent frameworks without months of prompting hacks.

10 min · Reviewed 2026

Why function calling matters more than chat quality

What the Hermes format looks like

Pattern (illustrative, not exact tags): [SYSTEM] You have access to the following tools: search_inventory(query: string) -> list of items send_email(to: string, subject: string, body: string) [USER] Find us 5 size 10 hiking boots and email John the list. [MODEL] <tool_call> search_inventory({"query": "size 10 hiking boots"}) </tool_call> [HARNESS RETURNS] [ {sku: , name: }, ] [MODEL] <tool_call> send_email({"to": "john@", "subject": "Boots", "body": ""}) </tool_call>The dance is the same in any tool-using model. Hermes documents the exact grammar in its model card.

Where it shines

Building agents that should work without an OpenAI dependency.
Self-hosted assistants where the tool list is sensitive (internal databases, private endpoints).
Cost-sensitive agent workloads — Hermes 8B handles a lot of routine tool calls cheaply.
Latency-sensitive use cases on dedicated hardware — local inference avoids round-trip to a cloud API.

Where to be careful

Risk	What goes wrong	Mitigation
Schema drift	Model emits a slightly malformed tool call	Validate every call against the schema before executing
Hallucinated tool names	Model invents a tool you didn't declare	Allowlist tool names; refuse anything else
Argument hallucination	Model fills required fields with plausible-but-wrong values	Prompt to confirm before destructive actions
Multi-step planning	Model gets confused after 3-4 tool calls	Use a smaller plan-then-execute split or a larger model for planning

Applied exercise

Read the function-calling section of the Hermes model card for the version you run.
Implement a single tool — a fake 'lookup_user(id)' that returns canned data.
Wire Hermes to call it and verify the model emits the documented format.
Add a deliberately invalid tool call to your test set and confirm your harness rejects it gracefully.

The big idea: Hermes makes open-weight tool use practical. The work is in the harness — validate everything, allowlist always.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-hermes-function-calling-creators

What is the main idea of "Hermes For Function Calling: Tool-Use Without OpenAI"?
1. Hermes ships with a documented function-calling format.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "Hermes For Function Calling: Tool-Use Without OpenAI"?
1. tool use
2. function calling
3. structured grammar
4. agent frameworks
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Building agents that should work without an OpenAI dependency.
4. Treat the AI output as automatically correct
What should a careful learner remember about "Validate, don't trust"?
1. Use "Validate, don't trust" as a reminder to verify the AI output before anyone relies on it.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about function calling be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about function calling.
Which action would help you apply "Hermes For Function Calling: Tool-Use Without OpenAI" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Self-hosted assistants where the tool list is sensitive (internal databases, private endpoints).

← Back to interactive lesson