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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NousResearch/hermes-agentnpx agentmods add skills/nousresearch/hermes-agent/torchtitanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nousresearch/hermes-agent/torchtitan)<a href="https://agentmods.dev/skills/nousresearch/hermes-agent/torchtitan"><img src="https://agentmods.dev/badge/skills/nousresearch/hermes-agent/torchtitan.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.02944 |
| Opus 5 | $0.00010 | $0.01472 |
| Sonnet 5 | $0.00004 | $0.00589 |
| Haiku 4.5 | $0.00002 | $0.00294 |
Grade A, and why
torchtitan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
3 near-identical copies found in the catalogue:
- torchtitan — 100% identical, 0 lines differ
- torchtitan — 100% identical, 0 lines differ
- distributed-llm-pretraining-torchtitan — 94% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TorchTitan - PyTorch Native Distributed LLM Pretraining
Quick start
TorchTitan is PyTorch's official platform for large-scale LLM pretraining with composable 4D parallelism (FSDP2, TP, PP, CP), achieving 65%+ speedups over baselines on H100 GPUs.
Installation:
# From PyPI (stable)
pip install torchtitan
# From source (latest features, requires PyTorch nightly)
git clone https://github.com/pytorch/torchtitan
cd torchtitan
pip install -r requirements.txt
Download tokenizer:
# Get HF token from https://huggingface.co/settings/tokens
python scripts/download_hf_assets.py --repo_id meta-llama/Llama-3.1-8B --assets tokenizer --hf_token=...
Start training on 8 GPUs:
# Configs are selected by name from the Python config registry
# (torchtitan/models/llama3/config_registry.py), not by TOML path
MODULE=llama3 CONFIG=llama3_8b ./run_train.sh
Common workflows
Workflow 1: Pretrain Llama 3.1 8B on single node
Copy this checklist:
Single Node Pretraining:
- [ ] Step 1: Download tokenizer
- [ ] Step 2: Configure training
- [ ] Step 3: Launch training
- [ ] Step 4: Monitor and checkpoint
Step 1: Download tokenizer
python scripts/download_hf_assets.py \
--repo_id meta-llama/Llama-3.1-8B \
--assets tokenizer \
--hf_token=YOUR_HF_TOKEN
Step 2: Configure training
In torchtitan's current layout, run configs are defined in a Python config registry
(torchtitan/models/llama3/config_registry.py) and selected by name via CONFIG=<name>
(or --config <name>). To customize, register your own config in the registry, or override
individual fields on the command line (e.g. --optimizer.lr 3e-4 --training.steps 1000).
The equivalent settings for an 8B run look like this (shown as fields; set them in the
registry entry or as --section.key value overrides):
# fields for a llama3 8B run (register in config_registry.py or pass as --overrides)
[job]
dump_folder = "./outputs"
description = "Llama 3.1 8B training"
[model]
name = "llama3"
flavor = "8B"
hf_assets_path = "./assets/hf/Llama-3.1-8B"
[optimizer]
name = "AdamW"
lr = 3e-4
[lr_scheduler]
warmup_steps = 200
[training]
local_batch_size = 2
seq_len = 8192
max_norm = 1.0
steps = 1000
dataset = "c4"
[parallelism]
data_parallel_shard_degree = -1 # Use all GPUs for FSDP
[activation_checkpoint]
mode = "selective"
selective_ac_option = "op"
[checkpoint]
enable = true
folder = "checkpoint"
interval = 500
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 389 lines · 20 tokens per session scan A 8a4ff6506bc5
torchtitan is a skill published in the GitHub repository NousResearch/hermes-agent (242,093 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 2,944 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
serving-llms-vllm
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.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
claude-api-in-prototypes
Call Claude from your HTML artifacts via window.claude.complete.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.