peace-orefejo/attest

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model judgment, not holistic LLM-judge guesswork), with confidence intervals.

语言：Python · GitHub 星标：19 · Fork：0

话题：agent-evaluation · ai-agents · anthropic · evals · evaluation · gemini · llm · llmops

在 GitHub 上查看原仓库