1. Conduid
  2. Files
  3. Hermes Rubric
MCP server · Files

Hermes Rubric

by · github.com/hermes-labs-ai/hermes-rubric

Evidence-first LLM-as-judge scoring for AI artifacts — papers, PRs, prompts, cold emails: synthesizes a rubric, collects quoted-evidence citations, scores only against that evidence, and hedges on thin evidence. Every dimension ties to a file:line or quote, with reproducibility receipts. 7 backends.

Unclaimed ai-agentsai-auditai-reliabilityai-safetycitationsclievalsevidence-firsthermes-labsllmllm-as-judgellm-evaluationllm-judgemcpprompt-engineeringpythonreproducibilitystructured-scoring
InstallView source
34Low

Scored 27 days ago · breakdown

About Hermes Rubric

Hermes Rubric is an MCP server published by hermes-labs-ai in the Files category: evidence-first LLM-as-judge scoring for AI artifacts — papers, PRs, prompts, cold emails: synthesizes a rubric, collects quoted-evidence citations, scores only against that evidence, and hedges on thin evidence. Every dimension ties to a file:line or quote, with reproducibility receipts. 7 backends.

The repository has 2 stars and 0 forks, with the last commit a month ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/hermes-labs-ai/hermes-rubric

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Hermes Rubric

Powered by Claude · Grounded in docs

I know everything about Hermes Rubric. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v1.2.3hermes-rubric 1.2.3 · 15 Sep 2026Fixed Stop the published quickstart recipe when `mktemp -d` fails, instead of continuing with an empty `$workdir` that made every quoted path expand to `/post.md` and `/result.json` (#32). `_documented_argv()` also now screens the…
v1.2.2Hermes Rubric v1.2.2 — OpenAI Agents SDK adapter and a scoring-fallback fix · 12 Sep 2026Hermes Rubric v1.2.2 — OpenAI Agents SDK adapter and a scoring-fallback fix Version 1.2.2 adds a native, optional adapter for the [OpenAI Agents SDK](https://openai.github.io/openai-agents-python/) and fixes a scoring-stage bug where…
v1.2.1Hermes Rubric v1.2.1 — Inspect AI scorer · 2 Sep 2026Hermes Rubric v1.2.1 — Inspect AI scorer Version 1.2.1 adds a native, optional scorer integration for [Inspect AI](https://inspect.aisi.org.uk/). What is new Install with `pip install "hermes-rubric[inspect]"`. Use the registered scorer as…
v1.2.0Hermes Rubric 1.2.0 — comparable re-grades · 2 Sep 2026What's Changed CI: pin actions and restrict workflow permissions by @roli-lpci in https://github.com/hermes-labs-ai/hermes-rubric/pull/13 CI: separate build validation from PyPI publish by @roli-lpci in…
v1.1.1Hermes Rubric v1.1.1 — Apache-2.0 successor release · 17 Aug 2026Hermes Rubric v1.1.1 — Apache-2.0 successor release Version 1.1.1 is the Apache-2.0 successor release of the portable assessment core introduced in v1.1.0. It preserves the existing package behavior, public APIs, CLI contract, evidence and…
Questions

About Hermes Rubric

How do I install Hermes Rubric?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Hermes Rubric safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Hermes Rubric still maintained?

Yes — the latest release is v1.2.3 (15 Sep 2026), and the last commit was a month ago. The repository has 2 stars.