lllm-evaluation

Here are 3 public repositories matching this topic...

RoboSathi / agentic-ai-series

Production-grade harness for governed AI agents, plus three agents built on it: customer support, research, and an MCP-driven ops analyst. Deterministic authority, claim-level hallucination checks, bounded loops, audit lineage, and evals graded against ground truth. Code for The Agentic AI Systems Series.

mcp ai-agents guardrails duckdb promptfoo hallucination-detection langgraph agentic-ai deepeval lllm-evaluation

Updated Oct 20, 2026
Python

mjtiv / structured-image-classifier

Star

Batch image classification pipeline using OpenAI vision with strict JSON schema, constrained labels, and cost tracking.

python json-schema vision openai image-classification structured-output multimodal ai-pipeline prompt-engineering lllm-evaluation controlled-ai

Updated Mar 22, 2026
Python

yagosamu / grounded-ops-copilot

Star

Production-grade engineering knowledge and incident copilot with measurable RAG quality, citations and bounded agents.

information-retrieval terraform incident-response multi-tenancy knowledge-management bm25 opensearch rag fastapi agentic-rag lllm-evaluation

Updated Oct 13, 2026
Python

Add this topic to your repo

To associate your repository with the lllm-evaluation topic, visit your repo's landing page and select "manage topics."

Learn more