v1.0.1

What's Changed

• feat: add framework adapters for LangGraph, LlamaIndex, and PydanticAI by @himmi-01 in #4

Full Changelog: v1.0.0...v1.0.1

v1.0.0

What's Changed

• feat: evalmonkey web ui and benchmark stability fixes by @himmi-01 in #3

Full Changelog: v0.1.3...v1.0.0

v0.1.3

implement automated eval asset generation and improvement prompts for failed benchmark traces ea99606
optimize benchmark loading by enabling streaming mode and add testing/inspection utilities 88a8fb5
strip markdown code fences from LLM judge responses 46be866
remove webarena benchmark 179d5ab

v0.1.2

add 5 chaos injection profiles and expand benchmark suite to 20 datasets with updated documentation and tests
add five new server-side chaos profiles and corresponding integration tests to evaluate agent resilience.

v0.1.1

Let users bring their own benchmark dataset and allow running all chaos tests via single CLI command 88fecf8

v0.1.0

EvalMonkey's first release with MCP server support.

• 8 Agent framework supported
• 10 of the shelf benchmarks supported
• 7 chaos scenarios supported
• benchmark historical data on TUI