AgentEvals
LangChain's open-source evaluators that score the sequence of messages and tool calls an agent made against a reference trajectory.
By LangChain, Inc. · github.com/langchain-ai/agentevals
Package download activity
AgentEvals has no PyPI or npm package that maps to it (SDK not mapped (its registry metadata does not link the vendor's domain or GitHub organisation)). This is not a zero.
Packages not measured
The vendor's docs name these packages, but their registry metadata does not link the vendor's domain or GitHub organisation, so under our mapping rule they are not counted. No download number is shown for them.
- PyPI
agentevals: registry metadata has no project/repository/homepage link (registry metadata, checked 2026-10-07) - npm
agentevals: registry metadata has no project/repository/homepage link (registry metadata, checked 2026-10-07)
GitHub stars
langchain-ai/agentevals: 740 stars (rank 35). Stars are a point-in-time count of a repository's bookmarks, not people using the tool.
Series starts 2026-W40 (740).
Facts
| Categories | Evaluation | |
|---|---|---|
| Status | Generally available | |
| Licence | MIT | source, checked 2026-10-07 |
| Self-host | Yes | source, checked 2026-10-07 |
| OpenTelemetry | Unknown | source, checked 2026-10-07 |
| Pricing model | free | |
| Entry price | Free; Open-source library; optional LangSmith integration is a separate LangChain product not priced here | source, checked 2026-10-07 |
| Free tier | Yes | |
| Measurability | SDK not mapped (its registry metadata does not link the vendor's domain or GitHub organisation) |
Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.
Compare
Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.