agentevals
Python Mediumagentevals-dev/agentevals
112 stars
10 forks
16 open issues
Active Apr 2026
Beginner-Friendly Issues 16
Issues tagged for new contributors
Create StreamingTraceManager once
#99 · Apr 1, 2026
techdebt
Add LabelModelGrader OpenAI Grader
#97 · Apr 1, 2026
enhancement
Add ScoreModelGrader OpenAI Grader
#96 · Apr 1, 2026
enhancement
Add StringCheckGrader OpenAI Grader
#95 · Apr 1, 2026
enhancement good first issue
Add LlamaIndex zero code example
#94 · Apr 1, 2026
good first issue
Add AWS AgentCore zero code example
#93 · Apr 1, 2026
good first issue
Add Pydantic AI zero code example
#92 · Apr 1, 2026
good first issue
enhancement
Support BYO evals on the UI
#87 · Apr 1, 2026
enhancement question UI
Expose all tool_trajectory_avg_score match types
#84 · Apr 1, 2026
enhancement ADK
(chore): Break streaming/ws_server.py into smaller classes
#77 · Mar 31, 2026
techdebt
Feature — MCP-based trace source for observability backends
#67 · Mar 26, 2026
enhancement
add README.md to src/agentevals so it shows up in pypi
#62 · Mar 23, 2026
add an evaluator for skills
#57 · Mar 20, 2026
enhancement
Add test coverage for MCP server tools
#40 · Mar 20, 2026
Eval Set from live sessions greyed out
#8 · Mar 9, 2026
waiting-for-feedback-from-submitter