Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/shaivpidadi/freeridev3/hermesgit clone --depth 1 https://github.com/Shaivpidadi/FreeRideV3Wrote 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/agents/shaivpidadi/freeridev3/hermes)<a href="https://agentmods.dev/agents/shaivpidadi/freeridev3/hermes"><img src="https://agentmods.dev/badge/agents/shaivpidadi/freeridev3/hermes.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 | $0.00000 | $0.01189 |
| Opus 5 | $0.00000 | $0.00594 |
| Sonnet 5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
hermes 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes — identification + config
Issue source
Shaivpidadi/FreeRide#11 — opened 2026-04-11 by lewdon, OPEN, no comments.
Title: hermes agent support?
Body (full): How to modify for hermes agent ?
The issue gives no link or context. Identification done by external search.
Identification
Hermes Agent by Nous Research — confidently identified.
- Repo: https://github.com/NousResearch/hermes-agent
- Stars: ~136k (top hit by far for
hermes agent) - Description: "The agent that grows with you"
- Homepage: https://hermes-agent.nousresearch.com
- Language: Python
- Topics include
openclaw, confirming same ecosystem niche as the FreeRide v2 host. Multiple companion repos (hermes-webui,hermes-desktop,hermes-workspace,hermes-agent-self-evolution, etc.) and a "Cowork" app explicitly bundling "OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI" (iOfficeAI/AionUi, 23k stars).
Ruled out:
- Nous Research Hermes models (e.g.
Hermes-3-Llama-3.1-70B) — those are LLMs, not agents. - HermesJS / Hermes JS engine / unrelated
hermesrepos — none have agent semantics or audience overlap with FreeRide.
Configuration approach
Hermes is explicitly designed to accept arbitrary OpenAI-compatible base URLs. No reverse-engineering required.
Two-layer config:
~/.hermes/config.yaml— model + provider + base_url (durable user config).env(project- or home-local) — API keys; takes precedence over yaml for credentials- Project-local
cli-config.yaml— overrides
Relevant fields (verbatim from cli-config.yaml.example in the repo):
model:
default: "openrouter/free"
provider: "custom" # any OpenAI-compatible endpoint
base_url: "http://localhost:11343/v1"
# api_key: "your-key-here" # optional; falls back to env
The example explicitly documents "custom" - Any other OpenAI-compatible endpoint. Set base_url below. with aliases ollama, vllm, llamacpp all mapping to custom. So Hermes' provider abstraction is FreeRide-shaped out of the box.
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.
- 4d ago First seen · 90 lines · 0 tokens per session scan A 365327e4515f
hermes is an agent published in the GitHub repository Shaivpidadi/FreeRideV3 (42 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,189 tokens. 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 2026-08-30.
Other agents, from other repositories
AGENTS
Every ProcessingContext carries an AgentMemory instance at context.memory. It is the single source of truth for everything shared between steps, tasks, sub-agents, and tools. Do not introduce a parallel result map in any executor — read and write through context.memory.
agent
Agent "agent" from nodetool-ai/nodetool, covering description, properties, outputs and related nodes.
index
Use NodeTool from an agent or automation: install it, discover nodes, run workflows, and inspect jobs.
classifier
Agent "classifier" from nodetool-ai/nodetool, covering description, properties, outputs and related nodes.
enhanceprompt
Agent "enhanceprompt" from nodetool-ai/nodetool, covering description, properties, outputs and related nodes.
extractor
Agent "extractor" from nodetool-ai/nodetool, covering description, properties, outputs and related nodes.