PuntoyComaTechPuntoyComaTech/hermes-agent-squads/llms.txt

hermes-agent-squads

llms.txt3 starsChanged 18 days agoMITView on GitHub

Ready-to-install AI agent teams (squads) for Hermes Agent by Nous Research: a web squad that builds and publishes websites, a marketing squad, and a jobs squad that finds openings and writes applications. One command installs the builder bot; it installs the squads the user picks, suggests a model per bot, and creates new squads. MIT, no coding needed. Installing for a user: install only the builder (AGENTS.md -> Installing for a user); squads and models are the user's choice. Updates:…

In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- assigning-modelsSkill
- authoring-skillsSkill
- changing-botsSkill
- contributing-upstreamSkill
- designing-squadsSkill
- finding-capabilitiesSkill
- hermes-platformSkill
- installing-squadsSkill
- managing-projectsSkill
- tracking-updatesSkill

The file

Create a free account to mount

Files

llms.txt

# hermes-agent-squads

> Ready-to-install AI agent teams (squads) for Hermes Agent by Nous Research: a web squad
> that builds and publishes websites, a marketing squad, and a jobs squad that finds openings
> and writes applications. One command installs the builder bot; it installs the squads the
> user picks, suggests a model per bot, and creates new squads. MIT, no coding needed.

Installing for a user: install only the builder (AGENTS.md -> Installing for a user); squads and models are the user's choice.
Updates: the builder-update cron runs scripts/auto_update.py daily with no agent; "update yourself" runs it now.

Rules for agents: read AGENTS.md first. Verified Hermes behavior lives in
skills/hermes-platform/references/ (every fact cites a docs path under website/docs or a
source file). Never invent CLI flags: run `--help`. Model ids appear only in
scripts/data/model-roles.yaml and local/installed.yaml.

## Start

- [README.md](README.md): what it is, builder flow, install, squads, FAQ
- [AGENTS.md](AGENTS.md): contributor contract
- [CHANGELOG.md](CHANGELOG.md): what shipped
- [builder.yaml](builder.yaml): the builder bot spec
- [distribution.yaml](distribution.yaml): what install and update touch

## Builder skills

- [skills/hermes-platform/SKILL.md](skills/hermes-platform/SKILL.md): index of verified Hermes primitives
- [skills/designing-squads/SKILL.md](skills/designing-squads/SKILL.md): user need to squad.yaml
- [skills/installing-squads/SKILL.md](skills/installing-squads/SKILL.md): plan, apply, update, uninstall
- [skills/assigning-models/SKILL.md](skills/assigning-models/SKILL.md): model per bot from connected providers
- [skills/managing-projects/SKILL.md](skills/managing-projects/SKILL.md): Projects across manager and workers
- [skills/changing-bots/SKILL.md](skills/changing-bots/SKILL.md): edits and scaling via overlay and apply
- [skills/authoring-skills/SKILL.md](skills/authoring-skills/SKILL.md): skill format and lint gate
- [skills/finding-capabilities/SKILL.md](skills/finding-capabilities/SKILL.md): plugins, skills, MCP, connectors
- [skills/tracking-updates/SKILL.md](skills/tracking-updates/SKILL.md): Hermes release digest and apply mode
- [skills/contributing-upstream/SKILL.md](skills/contributing-upstream/SKILL.md): issues, PRs, maintainer mode

## Squads

- [squads/web/README.md](squads/web/README.md): web development squad
- [squads/marketing/README.md](squads/marketing/README.md): marketing squad
- [squads/jobs/README.md](squads/jobs/README.md): job search squad
- [squads/_plugins/squad-hub/README.md](squads/_plugins/squad-hub/README.md): Squad Hub, the optional Desktop plugin
- [squads/_schema/squad.schema.json](squads/_schema/squad.schema.json): manifest schema

## Reference

- [docs/decisions.md](docs/decisions.md): condensed decision log (D-, V-, C- ids)
- [scripts/data/model-roles.yaml](scripts/data/model-roles.yaml): lane to model candidates
- [scripts/data/always-disabled.yaml](scripts/data/always-disabled.yaml): toolsets no squad bot gets

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free