# NousResearch/Hermes-Function-Calling

Repository: https://github.com/NousResearch/Hermes-Function-Calling
Canonical: https://ross.abutalabs.com/products/hermes-function-calling
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2025-12-22T14:09:27+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 58, release rhythm 35, longevity 65
- inputs: {"age_days": 921, "days_push": 254, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1457, forks 213 (observed 2026-08-28T04:04:47.012941+00:00)

## What it is
A repository providing function-calling capabilities for the Hermes Pro large language models, including stock price and financial data tools built on yfinance. It supports schema-based tool use, JSON mode via Pydantic models, and easy addition of custom functions.

## Use cases
- make an LLM call functions like fetching stock prices
- add custom tools for Hermes model function calling
- get structured JSON output from a language model
- run function-calling inference from the command line
- build an agent that queries financial data
- convert python functions to OpenAI tool schemas

## When to choose
- you use Hermes Pro models and want native function calling
- you need a lightweight reference implementation of LLM tool use
- you want JSON-structured model output via Pydantic schemas

## When to avoid
- you need a production agent framework with orchestration and memory
- you use models without Hermes function-calling support
- you want a hosted API rather than local inference

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, agent-framework, sdk, developer-tools
- domain: large-language-models, fintech
- platform: python, cli, cross-platform
- tags: function-calling, hermes, tool-use, -mode, chatml, openai-tools, ai-agents, natural-language-processing

## Member repositories
- NousResearch/Hermes-Function-Calling (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:47.012941+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:35:32.067465+00:00, confidence not recorded.
  - readme: https://github.com/NousResearch/Hermes-Function-Calling (fetched 2026-08-28T04:04:47.012941+00:00, sha a76b3c374527)
- Data as of 2026-08-30T08:39:29.467469+00:00.