Report · marked 25 Aug 2026

NousResearch/hermes-agent

Solid foundations, held back in a few specific places.

Python · 236,338 stars · 10,289 files · branch main

84 /100 A-

Instructions 25/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup 20/20Whether an agent can install the project and get it running without a human. Full marks.Verification loop 22/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on static type checking.Context economy 9/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context and repository weight.Navigability 10/10How quickly anything new can orient itself. Full marks.

Higher is better. Accent marks what is costing you most.

Fix these first

File sizes fit in context

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

Repository weight

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Static type checking

A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.

The full marking

Every deduction below names the file or setting it came from.

Instructions 25/27 A+

Whether the repo tells an agent how to behave before it starts guessing.

✓Agent instruction file 12/12

AGENTS.md is present, which is the format the most tools read.

✗Instruction quality 10/12

Specific enough that an agent can act on it.

Worth fixing: it's 95k characters, which burns context on every single turn.

names the actual commands to run

uses headings, so an agent can skim it

includes copyable code blocks

✓README as an entry point 3/3

README has a clear getting-started section.

Setup 20/20 A+

Whether an agent can install the project and get it running without a human.

✓Deterministic install 6/6

package-lock.json pins the dependency tree.

Found package-lock.json

✓Discoverable commands 6/6

Commands are declared where an agent will look for them.

package.json scripts (postinstall, install:root, install:web, install:tui, install:desktop, audit:root…)

pyproject.toml scripts

scripts/ directory

✓Environment config 4/4

.env.example documents what the app needs to run.

✓Pinned runtime version 2/2

The language runtime version is pinned.

Found .nvmrc

✓Reproducible environment 2/2

dockerfile gives a known-good environment.

Verification loop 22/25 A

Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.

✓Tests exist 8/8

4429 test files against 7376 source files.

e.g. apps/desktop/e2e/at-rest-connection-token.spec.ts, apps/desktop/e2e/batch-clarify.spec.ts, apps/desktop/e2e/boot-failure.spec.ts

✓Test command is discoverable 7/7

An agent can find and run `npm run check`.

✓Continuous integration 4/4

30 GitHub Actions workflows define what "passing" means.

✓Lint and format rules 3/3

pyproject.toml encodes the house style.

✗Static type checking 0/3

No static type checking.

A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.

Context economy 9/20 C

Whether the repo fits in a context window, or fights it.

✓No committed build output 6/6

No generated directories committed.

✓.gitignore hygiene 3/3

.gitignore covers 129 patterns.

✗File sizes fit in context 0/6

102 source files are over 100KB.

A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.

gateway/run.py — 1493KB

cli.py — 986KB

hermes_cli/web_server.py — 781KB

✗Repository weight 0/5

About 777MB checked out. Large enough that cloning and searching are both slow.

Large binaries and vendored trees slow every operation an agent performs. Git LFS or a separate assets repo keeps the working tree navigable.

Here is your AGENTS.md

Drafted from what is actually in this repository: the install command from your lockfile, the commands you already declare, your real directory layout. Anything marked TODO needs a person. Save it at the root as AGENTS.md.

AGENTS.md — drafted for NousResearch/hermes-agent

undefined

Open the raw markdown or curl -o AGENTS.md agentreadme.com/draft/NousResearch/hermes-agent.md

Show the mark

The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.

[![agent ready](https://agentreadme.com/badge/NousResearch/hermes-agent.svg)](https://agentreadme.com/NousResearch/hermes-agent)

Other Python repositories, marked

vinta/awesome-python 81 A- TheAlgorithms/Python 66 B yt-dlp/yt-dlp 54 C+ Significant-Gravitas/AutoGPT 63 B microsoft/markitdown 46 C anthropics/skills 30 D

All Python repositories

Think this mark is wrong?

Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.

Open an issue, already filled in