agentmods.dev

NousResearch/hermes-agent

The agent that grows with you

About the project

Hermes Agent is an AI assistant that learns from its use by creating and improving skills, retaining knowledge, searching past conversations, and adapting to its users. It is for people who want to run an agent through a terminal or messaging platforms while connecting it to different AI models and scheduled tasks.

This repository also configures its own agents. See what hermes-agent tells them →

Open on GitHub hermes-agent.nousresearch.com
244kStars on the repository
200Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Sort RelevanceRecently updatedFewest tokensSecurity gradeRepo starsStars this weekTop rated 198 mods

polymarket

49

NousResearch/hermes-agent

Skill Claude CodeCodex

Query Polymarket: markets, prices, orderbooks, history.

not rated 244k +2.1k today A Snyk: warnSkillSpector: pass 18 tokens original MIT

pptx-author

50

NousResearch/hermes-agent

Skill Claude CodeCodex

Build PowerPoint decks headless with python-pptx.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 16 tokens original MIT

stocks

51

NousResearch/hermes-agent

Skill Claude CodeCodex

Stock quotes, history, search, compare, crypto via Yahoo.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 15 tokens original MIT

pokemon-player

53

NousResearch/hermes-agent

Skill Claude CodeCodex

Play Pokemon via headless emulator + RAM reads.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 13 tokens original MIT

fitness-nutrition

54

NousResearch/hermes-agent

Skill Claude CodeCodex

Workout planning, macros, and body metrics via wger/USDA.

not rated 244k +2.1k today A Snyk: warnSkillSpector: warn 20 tokens original MIT

neuroskill-bci

55

NousResearch/hermes-agent

Skill Claude CodeCodex

Use live BCI cognitive and mood state from NeuroSkill.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 18 tokens original MIT

fastmcp

56

NousResearch/hermes-agent

Skill Claude CodeCodex

Build, test, and deploy Python MCP servers.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 14 tokens original MIT

mcporter

58

NousResearch/hermes-agent

Skill Claude CodeCodex

List, auth, and call MCP servers/tools from the terminal.

not rated 244k +2.1k changed 8d ago A Snyk: warnSkillSpector: warn 16 tokens original MIT

accelerate

59

NousResearch/hermes-agent

Skill Claude CodeCodex

Run PyTorch training across GPUs with minimal changes.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 13 tokens original MIT

chroma

60

NousResearch/hermes-agent

Skill Claude CodeCodex

Embedding database for RAG and semantic search.

not rated 244k +2.1k today A Snyk: failSkillSpector: pass 12 tokens original MIT

clip

61

NousResearch/hermes-agent

Skill Claude CodeCodex

Zero-shot image classification and image-text search.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 11 tokens original MIT

evaluating-llms-harness

62

NousResearch/hermes-agent

Skill Claude CodeCodex

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 29 tokens original MIT

weights-and-biases

63

NousResearch/hermes-agent

Skill Claude CodeCodex

W&B: log ML experiments, sweeps, model registry, dashboards.

not rated 244k +2.1k today A Snyk: failSkillSpector: pass 21 tokens original MIT

faiss

64

NousResearch/hermes-agent

Skill Claude CodeCodex

Fast vector similarity search at billion scale.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 11 tokens original MIT

flash-attention

65

NousResearch/hermes-agent

Skill Claude CodeCodex

Speed up long-sequence transformer training and inference.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 14 tokens original MIT

guidance

66

NousResearch/hermes-agent

Skill Claude CodeCodex

Constrain LLM output with grammars; guarantee valid JSON.

not rated 244k +2.1k today A Snyk: failSkillSpector: pass 16 tokens original MIT

huggingface-tokenizers

67

NousResearch/hermes-agent

Skill Claude CodeCodex

Fast BPE/WordPiece tokenization and custom vocab training.

not rated 244k +2.1k today A Snyk: passSkillSpector: pass 19 tokens original MIT

llama-cpp

68

NousResearch/hermes-agent

Skill Claude CodeCodex

Use this skill for local GGUF inference, quant selection, or Hugging Face repo discovery for llama.cpp.

not rated 244k +2.1k today A Snyk: warnSkillSpector: warn 18 tokens original MIT

outlines

69

NousResearch/hermes-agent

Skill Claude CodeCodex

Outlines: structured JSON/regex/Pydantic LLM generation.

not rated 244k +2.1k today A Snyk: passSkillSpector: warn 17 tokens original MIT

serving-llms-vllm

70

NousResearch/hermes-agent

Skill Claude CodeCodex

Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

not rated 244k +2.1k today A Snyk: failSkillSpector: warn 27 tokens original MIT

instructor

71

NousResearch/hermes-agent

Skill Claude CodeCodex

Structured LLM outputs validated with Pydantic.

not rated 244k +2.1k today A Snyk: failSkillSpector: pass 13 tokens original MIT

lambda-labs

72

NousResearch/hermes-agent

Skill Claude CodeCodex

On-demand GPU cloud instances for ML training.

not rated 244k +2.1k today C SkillSpector: warn 13 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: