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
ZhangJinHaHaHa/AgentLens
AgentLens is a decentralized platform and marketplace designed to address trust issues within the AI Agent economy. It provides verifiable proof of an AI Agent's capabilities, security boundaries, and track record before users engage with them. The platform integrates several advanced technologies, including On-chain Audit Scores, Intel SGX TEE (Trusted Execution Environment) Attestation, and Zero-Knowledge Proofs (ZK), along with a Multi-Dimensional Dynamic Reputation Model (MDDRM). This combination ensures that Agent trust is not merely claimed but is cryptographically verifiable. The system features Dimensional Risk Profiling, which evaluates Agents across six dimensions: security, task execution, cognitive ability, environment interaction, engineering quality, and compliance, generating a comprehensive risk profile and scenario suitability recommendations. All sandbox audits are performed within hardware-isolated enclaves (Intel SGX TEE), with cryptographic proofs anchored on-chain to guarantee execution integrity. Zero-Knowledge Proofs (using circom and snarkjs) are employed to verify audit score calculations and Agent identity without revealing proprietary source code. The Dynamic Reputation Model maintains on-chain reputation scores that adjust based on audit results, user reviews, appeal outcomes, and time decay. AgentLens offers a trust-first marketplace frontend where buyers can browse, filter (by risk, TEE status, price, task type), and rent or purchase access to verified Agents. It also includes an intelligent recommendation system and a multi-dimensional comparison tool to help users make informed decisions. The architecture involves on-chain components (AgentRegistry, AgentMarketplace, ReviewRegistry, ZkAuditVerifier) on Polygon Edge and off-chain infrastructure for listening to requests, triggering audits in Docker sandboxes with LLM engines and Intel SGX M6ce, and generating ZK proofs.
https://github.com/ZhangJinHaHaHa/AgentLens
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.