What should I verify first?

Verify state transitions and rollback with one non-production task first.. Keep credentials out of the first run, record expected output, define cleanup, and use public sample data before real workloads.

What is the main risk?

May increase setup, validation, or first-run risk for the user.. Use upstream documentation and a sandbox validation path before adoption.

Developer Workflow · Public

hermes-agent

Q: What is hermes-agent?

hermes-agent is a Doramagic Project Pack for Task-state checks, agent collaboration boundaries, permission paths, delivery acceptance, and rollback guidance. It links the upstream repository, source-backed manual, prompt preview, AI context, and risk boundaries so users can evaluate the project before installation.

Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.

Developer workflowTask boardAgent collaborationState managementDelivery boundaries

Best fitDevelopers organizing code tasks, agent collaboration, or engineering state into a reviewable workflow.

Check whether this project matches your task before installing it.

What it can doTask-state checks, agent collaboration boundaries, permission paths, delivery acceptance, and rollback guidance

Review the portable capability path.

Before continuingVerify in a sandbox

Do not treat a preview pack as a proven local install.

GitHub snapshot185k stars

32k forks · 1.5k contributors

Doramagic.ai Last verification date: 2026-06-08 Verification method: source evidence, semantic profile, public page gate, and static build acceptance.

Official first step Read manual preview Source repository

Publication status · 2026-06-08

What is hermes-agent?

hermes-agent supports developer collaboration, task organization, or engineering workflow management.
Best fit: Developers organizing code tasks, agent collaboration, or engineering state into a reviewable workflow.
Not for: Not for browser automation or workflows without clear project-state boundaries.
Capability added to an AI workflow: Task-state checks, agent collaboration boundaries, permission paths, delivery acceptance, and rollback guidance
First safe verification step: Verify state transitions and rollback with one non-production task first.
Verification state: source, Quick Start, and sandbox install checks are recorded as passed.
Top risk: May increase setup, validation, or first-run risk for the user.
Evidence base: https://github.com/NousResearch/hermes-agent, https://github.com/NousResearch/hermes-agent#readme, Human Manual, Pitfall Log

Quick decision

Use this section to decide whether the project is worth a deeper read.

Best forDevelopers organizing code tasks, agent collaboration, or engineering state into a reviewable workflow.

Match the project to your task before installing it.

CapabilityTask-state checks, agent collaboration boundaries, permission paths, delivery acceptance, and rollback guidance

Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.

RepositoryNousResearch/hermes-agent

185k stars · 32k forks

What it can do

Translate the upstream project into concrete capabilities the user can judge before installing.

Overview and Quickstart

Related topics: System Architecture and Agent Loop, Deployment, Profiles, and Operations

Source: https://github.com/NousResearch/hermes-agent / Human Manual

System Architecture and Agent Loop

Related topics: Providers and Model Integrations, Messaging Gateway and Platforms, Tools, Toolsets, and Plugins

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Providers and Model Integrations

Related topics: System Architecture and Agent Loop, Tools, Toolsets, and Plugins

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Messaging Gateway and Platforms

Related topics: Frontend Surfaces (Desktop, Web, TUI), System Architecture and Agent Loop

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Tools, Toolsets, and Plugins

Related topics: System Architecture and Agent Loop, Skills, Memory, and the Learning Loop

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Sources: https://github.com/NousResearch/hermes-agent, Human Manual, Project Pack evidence, and downstream validation signals.

Community Discussion Evidence

Project-level external discussion stays visible on the detail page, not only inside the manual.

Stars185k stars

Forks32k forks

Contributors1.5k contributors

Licenseunknown

Community Discussion Evidence

12 source-linked items

Review these external discussions before using hermes-agent with real data or production workflows. They are review inputs, not standalone proof that the project is production-ready.

01
fix: skills hub hangs on network timeout + `hermes update` intermittent
github / github_issue
02
[Feature] goal_mode: remove hard turn cap — keep running until goal achi
github / github_issue
03
[skills-index-watchdog] Skills index is stale or degraded (degraded)
github / github_issue
04
[Bug]: Desktop "Remote gateway" can't connect over WebSocket — /api/ws a
github / github_issue
05
[Bug]: Fails to install NeuTTS during setup
github / github_issue
06
Hermes Agent v0.16.0 (2026.6.5) — The Surface Release
github / github_release
07
Hermes Agent v0.15.2 (2026.5.29.2)
github / github_release
08
Hermes Agent v0.15.1 (2026.5.29) — The Patch Release
github / github_release
09
Hermes Agent v0.15.0 (2026.5.28) — The Velocity Release
github / github_release
10
Hermes Agent v0.14.0 (2026.5.16)
github / github_release
11
Hermes Agent v0.13.0 (2026.5.7) — The Tenacity Release
github / github_release
12
Hermes Agent v0.12.0 (2026.4.30)
github / github_release

How to start

Only source-backed commands are shown here. Verify them in an isolated environment first.

Try the prompt first

Test the workflow without installing the upstream project.

preview

Read the Human Manual

Understand inputs, outputs, limits, and failure modes.

manual

Take context to your AI host

Use the compiled assets in your preferred AI environment.

context

Run sandbox verification

Confirm install commands and rollback before using a primary environment.

verify

pip install hermes-agent

Official start command · https://github.com/NousResearch/hermes-agent#readme · verified: yes

Human Manual

The English page must expose the real manual, not a short placeholder.

8+ sections · Human Manual

hermes-agent Manual

The agent that grows with you

Open the full manual

https://github.com/NousResearch/hermes-agent Project Manual
Table of Contents
Overview and Quickstart
Related Pages
What is Hermes Agent?
Quickstart
Terminal 1 — backend
Terminal 2 — Vite dev server with HMR

Overview and Quickstart

Related topics: System Architecture and Agent Loop, Deployment, Profiles, and Operations

Source: https://github.com/NousResearch/hermes-agent / Human Manual

System Architecture and Agent Loop

Related topics: Providers and Model Integrations, Messaging Gateway and Platforms, Tools, Toolsets, and Plugins

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Providers and Model Integrations

Related topics: System Architecture and Agent Loop, Tools, Toolsets, and Plugins

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Messaging Gateway and Platforms

Related topics: Frontend Surfaces (Desktop, Web, TUI), System Architecture and Agent Loop

Source: https://github.com/NousResearch/hermes-agent / Human Manual

Tools, Toolsets, and Plugins

Related topics: System Architecture and Agent Loop, Skills, Memory, and the Learning Loop

Source: https://github.com/NousResearch/hermes-agent / Human Manual

AI Context Pack and portable assets

After deciding to continue, take the project context into your own AI host.

Complete pack plus user-owned assets

These files are planning and verification assets for Claude Code, Codex, Gemini, Cursor, ChatGPT, and other AI hosts.

Download complete pack Read Human Manual

BundleComplete Project Pack AssetAI Context Pack AssetBoundary & Risk Card AssetHuman Manual AssetPitfall Log AssetPrompt Preview AssetQuick Start EvidenceREPO_INSPECTION.json

Preflight checks

Treat this page as a planning asset, not proof that your local environment is ready.

The manual is generated from source-linked project files and Doramagic validation signals.
Community evidence warnings stay visible instead of being converted into marketing claims.
This English page is indexable because the locale quality gate passed and explicit English index approval is enabled.
Use the upstream repository as the final authority for installation commands, license, and version-specific behavior.

Pitfall Log and verification risks

Doramagic surfaces high-risk items before users treat a candidate capability as verified.

high

Installation risk requires verification

May increase setup, validation, or first-run risk for the user.

high

Configuration risk requires verification

May increase setup, validation, or first-run risk for the user.

high

Security or permission risk requires verification

May increase setup, validation, or first-run risk for the user.

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: Hermes Agent v0.12.0 (2026.4.30)

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: Hermes Agent v0.13.0 (2026.5.7) — The Tenacity Release

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: Hermes Agent v0.14.0 (2026.5.16)

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: Hermes Agent v0.15.1 (2026.5.29) — The Patch Release

medium

Installation risk requires verification

Upgrade or migration may change expected behavior: Hermes Agent v0.16.0 (2026.6.5) — The Surface Release