Production-readiness scorecard, eval templates, incident regressions, and MCP safety checks for AI agents. EN/中文.

0 stars 0 forks 0 watchers JavaScript MIT License
agent-evaluation agentic-ai ai-agent ai-engineering ai-safety developer-tools evals human-in-the-loop llm llm-security mcp model-context-protocol production prompt-injection scorecard
3 Open Issues Need Help Last updated: Aug 16, 2026

Open Issues Need Help

View All on GitHub
help wanted failure-case

Production-readiness scorecard, eval templates, incident regressions, and MCP safety checks for AI agents. EN/中文.

JavaScript
#agent-evaluation#agentic-ai#ai-agent#ai-engineering#ai-safety#developer-tools#evals#human-in-the-loop#llm#llm-security#mcp#model-context-protocol#production#prompt-injection#scorecard
help wanted good first issue

Production-readiness scorecard, eval templates, incident regressions, and MCP safety checks for AI agents. EN/中文.

JavaScript
#agent-evaluation#agentic-ai#ai-agent#ai-engineering#ai-safety#developer-tools#evals#human-in-the-loop#llm#llm-security#mcp#model-context-protocol#production#prompt-injection#scorecard
help wanted good first issue

Production-readiness scorecard, eval templates, incident regressions, and MCP safety checks for AI agents. EN/中文.

JavaScript
#agent-evaluation#agentic-ai#ai-agent#ai-engineering#ai-safety#developer-tools#evals#human-in-the-loop#llm#llm-security#mcp#model-context-protocol#production#prompt-injection#scorecard