Community Evaluators

Browse and use community-contributed evaluators, or submit your own.

9 evaluators · Last updated: Mar 23, 2026 · View on GitHub ↗
py

contains

by agentevals-dev

Scores whether each final response contains a configured substring (case-sensitive or case-insensitive)

string contains
py

equals

by agentevals-dev

Scores whether each final response exactly matches a configured expected string

string equals
py

is_json

by agentevals-dev

Scores whether each final response parses as JSON (optional markdown code fence extraction)

json structured
py

levenshtein_ratio

by agentevals-dev

Scores similarity of each response to a reference string using normalized Levenshtein distance

string levenshtein
py

random_evaluator

by peterj

Example evaluator that returns a randopm score between 0 and 1

test
py

regex_match

by agentevals-dev

Scores whether each final response matches a configured regular expression

regex
py

response_quality

by agentevals-dev

Checks that responses are non-empty, meet a minimum length, and don't just echo back the user input

quality response length
py

tool_coverage

by agentevals-dev

Verifies that each invocation made at least a minimum number of tool calls

tools coverage validation
py

tool_sequence_match

by agentevals-dev

Scores whether tool calls match an expected list of tool names (order-sensitive or multiset)

tools trajectory

Using Community Evaluators

1

Reference in eval config

evaluators:
  - name: response_quality
    type: remote
    source: github
    ref: evaluators/response_quality/response_quality.py
    threshold: 0.7
    executor: local
    config:
      min_response_length: 20
2

Run as usual

agentevals run traces/my_trace.json \
  --config eval_config.yaml \
  --eval-set eval_set.json

Evaluators are downloaded automatically and cached in ~/.cache/agentevals/evaluators/.

Build Your Own Evaluator

Evaluators are standalone scoring programs that read EvalInput JSON from stdin and write EvalResult JSON to stdout. Scaffold one in seconds:

pip install agentevals-cli
agentevals evaluator init my_evaluator