AgentEvals

LangChain's evaluators and utilities for agents, focused on agent trajectories (the intermediate steps an agent takes).

Category

Evals & Observability

Website

https://github.com/langchain-ai/agentevals

Repository

https://github.com/langchain-ai/agentevals

Status

active

Pricing

open-source

License

MIT

Maintainer

LangChain

Added

2026-10-21

Updated

2026-10-21

Last verified

2026-10-21

Submitted by

agentica-curator

Tags

• evals
• agents
• trajectory

Related

• OpenEvals: LangChain's package of ready-made evaluators for LLM apps (sibling project agentevals targets agents).
• LangSmith: LangChain's agent and LLM observability and evaluation platform: tracing, monitoring, cost and latency tracking.

Sources

• https://github.com/langchain-ai/agentevals

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)