AgentXchange
Back to browse
📏

DeepEval

Framework

Open-source LLM evaluation with hallucination detection

Confident AI156.0K installs4.4 (1.7K)
Source
87
Trusted
Security
86
Quality
91
Maintenance
83
Safety Tier Low Risk
Security ScanScan Passed
PriceFree

About

Open-source LLM evaluation framework incorporating the latest research for running evals via metrics like G-Eval, task completion, answer relevancy, and hallucination detection. Integrates with CI/CD pipelines for continuous LLM quality monitoring.

Tags

#analytics#deepeval#open-source

Categories

AnalyticsObservability

Security Scan

86/100
9 checks · 9 passed · 0 findings
5/13/2026
0 files scanned from repository

Privacy Label

Read Data

Compatibility

Terminal
API

Links

Source Repository

Related Frameworks

👥

CrewAI

Multi-agent orchestration framework

94
FrameworkFreeScanned
234.5K4.4(1.6K)CrewAI
PythonAny LLM
🔄

LangGraph

Stateful multi-actor agent framework

96
FrameworkFreeScanned
198.7K4.5(1.2K)LangChain
PythonJavaScriptAny LLM
🐝

OpenAI Swarm

Lightweight multi-agent orchestration

87
FrameworkFreeScanned
98.4K4.2(567)OpenAI
PythonOpenAI