alizahidraja/isnad

[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.

50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.

Middleware for AI Agents that verifies grounding and prevents hallucinations. Returns structured retry suggestions for self-correction.

Evaluation and Tracking for LLM Experiments and AI Agents

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

The LLM Evaluation Framework

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstream agents detect 100% of errors and retry to achieve a 50% jump in answer accuracy.

Supercharge Your LLM Application Evaluations 🚀

Readymade evaluators for your LLM apps