Assayevidence-based project evaluation

hermes-agent/hermes

https://github.com/hermes-agent/hermes · revision 0123456789ab

Anonymous profilePublicOpenAI API
Evaluator profile
openai-project-evaluator-1
Model
gpt-project-eval
Rubric
project-rubric-1
Project type
cli_developer_tool
Maturity
stable
Tags
agent, automation, developer_tool

Introduction

  • Hermes Agent is a multi-gateway automation agent with a skill and tool system.
  • It targets operators wiring language-model agents into chat and workflow platforms.

Scores

The Assay Score never replaces its dimensions, and Potential is a separate forward-looking indicator.

Assay Score0/ 100Scored · confidence 82% (high)
  • Project Substance90confidence 85% (high)
  • Originality72confidence 60% (medium)
  • Engineering Rigor86confidence 78% (high)
  • Open Source Readiness84confidence 74% (high)
  • Maintenance Health83confidence 70% (high)
  • Potential80confidence 62% (medium)

Evidence

Every record below is graded, revision-pinned, and citable by the scores above.

Repository snapshot (1)
evidence:repository:snapshot
evidence:repository:snapshotcomplete · grade A
Files (2)
src/agent.ts
evidence:file:src-agent-tscomplete · grade A
src/gateway.ts
evidence:file:src-gateway-tscomplete · grade A
Repository features (4)
readme
evidence:feature:readmecomplete · grade B
license
evidence:feature:licensecomplete · grade B
ci
evidence:feature:cicomplete · grade B
security_policy
evidence:feature:security_policycomplete · grade B

Similar projects

A one-depth functional cohort. Similarity measures comparability, not quality, and never implies misconduct. Popularity is context only.

  1. other-org/autopilot

    78% similar · confidence 75%

    Selected because of problem overlap, feature overlap, technical similarity

    problem overlap
    90% similar
    feature overlap
    70% similar
    technical similarity
    80% similar
    structural similarity
    not available (unavailable)

    This project only: json output

    Candidate only: web dashboard

    Adoption context: 4200 stars

  2. other-org/chatops-bot

    62% similar · confidence 60%

    Selected because of problem overlap, feature overlap, structural similarity

    problem overlap
    60% similar
    feature overlap
    50% similar
    technical similarity
    not available (unavailable)
    structural similarity
    70% similar

    This project only: json output

    Candidate only: web dashboard

    Adoption context: 1200 stars

  3. other-org/task-runner

    50% similar · confidence 40%

    Selected because of problem overlap, technical similarity

    problem overlap
    50% similar
    feature overlap
    not available (unavailable)
    technical similarity
    50% similar
    structural similarity
    not available (unavailable)

    This project only: json output

    Candidate only: web dashboard

    Adoption context: 300 stars

Additional candidates (1)
  • other-org/adjacent-tool30% similar · confidence 40%

Cite this result

The badge states the engine profile, score, and provisional, stale, or insufficient-evidence state, and links back to this engine-specific result.

assay: OpenAI API 88/100assay: OpenAI API88/100

Prefix the badge and result paths with the deployment origin when embedding in a remote README.

Warnings and limitations

  • repository_code_not_executed

Assay evaluates the project, not its authors or their use of AI-assisted development tools. Scores are dimensioned, versioned, and grounded in cited evidence.