abhiai-git/agent_trajectory_evaluation
agent_trajectory_evaluation is a Python package designed to evaluate the reasoning trajectories of tool-enabled LLM agents, Traditional evaluation methods often focus solely on final-answer accuracy, overlooking how an agent arrives at its conclusions. trajectory-eval addresses this by analyzing the entire reasoning process — step-by-step
17
/ 100
Experimental
No Package
No Dependents
Maintenance
6 / 25
Adoption
0 / 25
Maturity
11 / 25
Community
0 / 25
Stars
—
Forks
—
Language
Python
License
MIT
Category
Last pushed
Oct 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/abhiai-git/agent_trajectory_evaluation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.