hermescheck
huangrichao2020/hermescheck
Architecture and runtime health checks for Hermes Agent checkouts, forks and deployments
hermescheck is a community static-analysis tool that scans an AI agent checkout and reports architecture problems such as memory drift, tool-boundary gaps, gateway risks and scheduler behavior. Hermes Agent is its primary target, and it can also render a PNG report card.
What hermescheck does
hermescheck scans an agent repository and produces a structured architecture report covering memory drift, tool-boundary gaps, runtime sprawl, gateway risks, scheduler behavior and observability. Its checks are shaped around Hermes Agent forks and deployments and ask Hermes-specific questions: whether the core runtime surfaces are still present, whether slash commands come from the central registry, whether CLI, TUI, gateway, skills, cron and SessionDB still line up, and whether interrupted runs can resume.
Results can be exported as JSON, Markdown and SARIF for GitHub code scanning, or rendered as a PNG report card for README images and release posts. A --profile flag selects a scan profile, and the README example uses personal. The project is derived from the general-purpose agchk scanner, says it is not an official Nous Research project, and states a plan to update its checks with each Hermes release.
Key features
- Architecture audit across memory, tool boundaries, gateway, scheduler and observability
- Hermes-specific checks for command registry, CLI, TUI, gateway, skills, cron and SessionDB alignment
- JSON, Markdown and SARIF exports
- PNG report card rendering
- Scans any agent repository, not only Hermes
When to use it
- Auditing a Hermes Agent fork for drift from the core runtime surfaces
- Adding a repeatable architecture check to a release or review workflow
- Publishing a report card image in a README or release post
Who it is for: Maintainers of Hermes Agent forks and deployments, and developers of other long-running agent runtimes, who want repeatable architecture reviews.
How it fits with Hermes Agent
A community companion tool whose strongest checks target Hermes Agent checkouts, forks and deployments. It is not an official Nous Research project.
How to install hermescheck
These commands are copied from the project's README. Check the repository for the latest steps before you run them.
pip install hermescheckNote: The README states it is not an official Nous Research project and that it is derived from the general-purpose agchk scanner.
FAQ
What is hermescheck?
hermescheck is a tool that produces architecture audit cards for AI agent runtimes. It scans a checkout and reports on memory drift, tool-boundary gaps, runtime sprawl, gateway risks and scheduler behavior.
Does hermescheck work with Hermes Agent?
Yes. Hermes Agent is its first deep adaptation target, and its strongest checks are shaped around Hermes forks, deployments and review workflows. It is a community tool and not an official Nous Research project.
How do I install hermescheck?
Run pip install hermescheck. Then scan a checkout with hermescheck ./path/to/agent-repo, optionally adding --profile personal, -o audit_results.json and -r audit_report.md for output files.
Similar dev tools for Hermes Agent
All dev toolsGovernance harness with a gated plan-to-ship pipeline for agent fleets on Claude Code, Codex, Grok or Hermes
0xNyk openclaw-to-hermesMigration tool that moves an OpenClaw setup to Hermes Agent, with dry-run and backup
nicolasmelo1 LogionDeveloper tooling for a registry that measures whether AI-agent skills and plugins actually work
BULDEE AI Craftsman SuperpowersArchitecture gate for AI coding agents that blocks writes breaking DDD and Clean Architecture rules
vector4wang EdgeGlowmacOS menu bar app that lights up your screen edges while Claude Code or Hermes Agent is working
magicwubiao go-magicGo AI agent framework inspired by Hermes Agent, with a TUI, web dashboard and messaging gateway
Related guides: How to install Hermes Agent · Run multiple Hermes agents with profiles