BlackRoad-Agents/agent-eval

agent eval — Part of the BlackRoad OS ecosystem. Sovereign computing, edge AI, mesh networking. blackroad.io

22
/ 100
Experimental

Provides automated evaluation of local AI agents running on Ollama, scoring responses against keyword-based test cases to measure accuracy, relevance, and latency across 20 distributed agent types (coder, researcher, mathematician, etc.). The harness ingests JSON test definitions, queries agents via HTTP, and generates scored reports with configurable model selection and custom test file support—designed for validating agent performance in the sovereign, edge-first BlackRoad ecosystem without external dependencies.

No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

Last pushed

Mar 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/BlackRoad-Agents/agent-eval"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.