Company research
As of June 10, 2026
GitHub commits increased 146.5% over the last 30 days.
Confident AI
LLM evaluation framework with the DeepEval testing library
AI InfrastructureFounded 2023#15 of 55 in AI Infrastructure
Updated June 10, 2026
Follow this company
Follow this company to revisit its latest research cards from your account.
Company profile
What is Confident AI?
Confident AI provides an LLM evaluation framework, primarily through its open-source DeepEval library, to help developers test and evaluate their large language model applications. They also offer the Confident AI Platform, an enterprise solution for advanced LLM evaluation, monitoring, and guardrails, aiming to ensure the reliability and safety of AI systems in production.
History
Research history
7 research updates
History
Research history
Ai Infrastructure
Confident AI: GitHub commits increased 114.6% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 86.4% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 104.9% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 97.7% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 104.9% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 85.4% over the last 30 days
1 metricAi Infrastructure
Confident AI: GitHub commits increased 82.5% over the last 30 days
1 metricLatest company data
Primary data point
Package downloads (30d)Metric: PyPI downloadsSource: PyPI BigQueryScope: UTC activity dayUpdates: DailyFreshness: 48h target; 48h expected source lagConfidence: HighCaveat: Includes all package installations including CI/CD pipelines and mirrors; pypistats is fallback only.Methodology →
5.3M/30d
Tracked package: PyPI deepeval
▲ +58%Updated 2d ago
Other data points
Dependent projectsMetric: PyPI dependentsSource: Libraries.io APIScope: UTC daily snapshotUpdates: DailyFreshness: 48h target; 48h expected source lagConfidence: HighCaveat: Counts direct reverse dependencies from PyPI.Methodology →
120
Projects depending on tracked package: PyPI deepeval
Updated 1d ago
GitHub starsMetric: GitHub starsSource: GitHub GraphQL + GH ArchiveScope: UTC daily snapshotUpdates: DailyFreshness: 48h target; 24h expected source lagConfidence: HighCaveat: Stars are bookmarks, not usage.Methodology →
16.1K
Main repository stars
Updated 1d ago
Daily public-repo contributorsMetric: Daily public-repo contributorsSource: GH ArchiveScope: UTC activity dayUpdates: DailyFreshness: 48h target; 36h expected source lagConfidence: MediumCaveat: Daily public PushEvent activity for designated repos; not a full engineering headcount or trailing-window contributor total.Methodology →
1
Distinct GitHub PushEvent actors in tracked public repos
▼ -71%Updated 1d ago
Repository health
Maintenance data from the main open-source repository.
Releases (30d)Source: GitHub release dataUpdates: WeeklyCaveat: Published releases in the last 30 daysMethodology →
0
Repository usage
Public repositories and source files importing packages tied to Confident AI.
Repos importingMetric: Public GitHub repos using company packagesSource: ecosyste.ms Packages APIScope: UTC daily snapshotUpdates: DailyFreshness: 48h target; 48h expected source lagConfidence: HighCaveat: Public GitHub dependency data only; private repos and direct API use outside those packages are not visible.Methodology →
10%
About Confident AI
Confident AI provides an LLM evaluation framework, primarily through its open-source DeepEval library, to help developers test and evaluate their large language model applications. They also offer the Confident AI Platform, an enterprise solution for advanced LLM evaluation, monitoring, and guardrails, aiming to ensure the reliability and safety of AI systems in production.
FoundersKevin Kwok, Kevin Li
Funding
$500K · 1 roundRaised $500K total. Category position #15 of 55 in AI Infrastructure.
Seed2023
$500KY Combinator
Investors
Y Combinator
Tracked packages (1)
1 PyPI
deepeval
PyPIMain PyPI packagedeepeval
LLM evaluation framework with the DeepEval testing library