agentevals-dev / agentevals
agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces
Why this job: topics: evaluation, evals, tracing
What it does
Send OTLP traces. Score what your agent did. Get the results back as OpenTelemetry GenAI eval events. No SDK, no reruns, no platform to host.
Get started
pip install agentevals-cli
# CLI, REST API, OTLP receivers, embedded web UI
pip install "agentevals-cli[live]"
# adds the MCP server- Maintenance
- Active
- Last commit 4 days ago
- Stars
- 169
- +1 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.12.0
- Released 5 days ago
- Built with
- Python
- 75% of the code
Is it looked after?
- Contributors
- 9
- Last 90 days
- Issues
- 74% closed
- 21 still open
- Pull requests
- 161 merged
- 0 waiting
- Releases
- 40
- 30+ in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Jwuthri / Tracely-ai | 1,299 | yesterday | MIT | No downloads |
| future-agi / traceAI | 266 | today | Apache-2.0 | No downloads |
| using-system / otelyssey | 118 | yesterday | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 75%
- TypeScript 24%
- Makefile <1%
- CSS <1%
Topics
- agentevals
- agents
- evals
- evaluation
- genai
- llm
- llm-as-judge
- opentelemetry
- otel
- tracing
Project record
- JobEvals and observability
- StatusListed
- Commits464
- Forks28
- Watching1
- Stars in 28 days+7
- CreatedFeb 24, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026