promptfoo/promptfoo
Promptfoo is a CLI and library for evaluating LLM applications, offering automated testing, red teaming, and vulnerability scanning for prompts, models, agents, and RAGs.
Awesome Infra for AI › LLM Evaluation & Testing
Jwuthri/Tracely-ai
Tracely turns production agent traces into a regression test suite instead of asking engineers to hand-author evaluation datasets. Traces arrive over plain OTLP with agent semantics such as agent and conversation identifiers, and every run is graded as it lands. Failing runs are clustered into issues so that one recurring defect does not appear as hundreds of unrelated incidents. A failure can then be promoted to a case: the trace is frozen into a hermetic fixture that records the exact input, the exact tool calls and the exact model responses, so replaying it in continuous integration costs nothing and calls no live model. Those cases run on every pull request, and a regression blocks the merge rather than moving a number on a dashboard. Alerts go out over Slack, email or a webhook when a new failure cluster appears or a gate flips. The application is organised as five views that follow the loop: observe traces hierarchically, detect and cluster failures, manage frozen cases, read continuous integration verdicts, and watch trends over time. The whole stack is self-hostable in one deployment, comprising the API, a worker, the user interface, Postgres, ClickHouse, Redis and MinIO, with a one-click template for a hosting platform. A Python package instruments applications, and an agent skill teaches coding assistants how to work with the system. Tracely suits teams whose agents already run in production and who want the failures they observe to become permanent, cheap tests rather than dashboard entries someone has to remember to act on.
https://github.com/Jwuthri/Tracely-ai
Also in LLM Evaluation & Testing
ifixai-ai/iFixAi
iFixAi is a diagnostic tool that evaluates AI models and agents for operational misalignment, including fabrication, manipulation, deception, unpredictability, and opacity, by running up to 45 insp...
confident-ai/deepeval
DeepEval is an open-source LLM evaluation framework, offering a variety of metrics and tools for assessing the performance of AI agents, RAG pipelines, and chatbots through unit testing.
vibrantlabsai/ragas
Ragas is an evaluation framework for LLM applications that provides objective metrics, test data generation, and feedback loops for continuous improvement.
NVIDIA/garak
Garak is an open-source LLM vulnerability scanner designed to red-team and assess generative AI models for weaknesses like hallucination, data leakage, prompt injection, and toxicity.
evidentlyai/evidently
Evidently is an open-source Python framework for evaluating, testing, and monitoring ML and LLM systems, providing comprehensive data and model quality checks from experiments to production.
open-compass/opencompass
Open-source LLM evaluation platform for running standardized benchmarks across models, with configurable datasets, prompt templates, and an official public leaderboard.
Giskard-AI/giskard-oss
Giskard is an open-source Python library for testing and evaluating agentic systems and LLM applications, offering tools for scenario-based testing, red teaming, and vulnerability scanning.