Apery – Synthetic Data Generator for AI Agents
Yet another synthetic data tool when Faker and Mockaroo already exist.

CSV-based agent testing works but LangSmith already owns this evaluation workflow.
AI engineers, ML teams
LangSmith · Braintrust · Arize Phoenix
You can now: • Upload CSVs with real inputs and expected outputs • Run your agent against those datasets • Generate new test cases from existing ones to cover edge cases
This makes it easier to test scenarios you were previously testing manually and catch regressions when your agent changes.
Demo below. Would love feedback from anyone building agents.
Yet another synthetic data tool when Faker and Mockaroo already exist.
Dependency-graph filtering cuts output tokens 63%, not just input—Claude stops narrating when focused.
Schema validation catches LLM output mismatches before they break downstream systems.
One-click firewall rules for 22 providers—no more hunting AWS/Azure/GCP feeds separately.
Runs with one npx command and immediately surfaces a helpful timeline view with token counts, tool I/O panes and subagent nesting — exactly the sort of visibility you want when an agent goes off the rails. Cleverly reads the local ~/.claude/projects traces so setup is trivial, but its usefulness is limited by being Claude-only and local; add search/aggregation or a team-sharing mode and this jumps up a tier.
MCP-native tool lets AI agents fetch and clean datasets without human intervention.