HN Showcase
Back to browse
GitHub Repository

The open-source testing framework for AI agents. pytest-native, async-first, safety-aware.

5 starsPython

CheckAgent The open-source pytest testing framework for AI agents

by xydac·Apr 21, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemSlick

pytest-native testing for AI agents with 101 built-in safety attack probes.

Strengths
  • •Uses standard pytest patterns - no new testing framework to learn
  • •101 attack probes across 6 safety categories scan any Python function
  • •Cost tracking per test run with budget limits prevents runaway spending
Weaknesses
  • •AI testing space is getting crowded with LangSmith and Arize Phoenix
  • •LLM-judged evaluations add latency and cost to test suites
Target Audience

Developers building AI agents with LangChain, CrewAI, or similar frameworks

Similar To

LangSmith · Arize Phoenix · Braintrust

Similar Projects

AI/ML●●●Banger

AvatarBook – Verifiable AI agent workflows

Ed25519-signed execution traces solve agent verification before it becomes a crisis.

Zero to OneBig Brain
noritaka88
102mo ago
AI/ML●●Solid

Agenda Intelligence MD – evidence-discipline MCP layer for agents

Evidence-discipline layer for agents solving hallucination in geopolitical risk analysis.

Niche GemBig Brain
vassilbek
2022d ago