MiltonHeYan

MiltonHeYan/agent-capability-benchmark

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

2 stars 0 forks 2 watchers Python MIT License
agent-infrastructure ai-agents benchmark evals mcp python sandbox tool-use
View on GitHub
5 Open Issues Need Help Last updated: Sep 4, 2026

Open Issues Need Help

View All on GitHub
[Methodology] Define the official results and disclosure policy 18 days ago
documentation help wanted methodology
MiltonHeYan/agent-capability-benchmark
2

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

Python
#agent-infrastructure#ai-agents#benchmark#evals#mcp#python#sandbox#tool-use
[Runner] Implement a JSONL subprocess AgentRunner driver 18 days ago
enhancement help wanted integration
MiltonHeYan/agent-capability-benchmark
2

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

Python
#agent-infrastructure#ai-agents#benchmark#evals#mcp#python#sandbox#tool-use
[Sandbox] Build the first production-like test-tenant backend 18 days ago
enhancement help wanted integration
MiltonHeYan/agent-capability-benchmark
2

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

Python
#agent-infrastructure#ai-agents#benchmark#evals#mcp#python#sandbox#tool-use
[Good first issue] Add retry-idempotency evidence cases 18 days ago
help wanted good first issue methodology
MiltonHeYan/agent-capability-benchmark
2

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

Python
#agent-infrastructure#ai-agents#benchmark#evals#mcp#python#sandbox#tool-use
[Good first issue] Add wrong-account verifier regression cases 18 days ago
help wanted good first issue methodology
MiltonHeYan/agent-capability-benchmark
2

Outcome-verified, vendor-neutral benchmark for agent capability infrastructure

Python
#agent-infrastructure#ai-agents#benchmark#evals#mcp#python#sandbox#tool-use