ML Testing
478AI tools in the ML Testing category
ai-planning-val
jan-dolejsi
Javascript/typescript wrapper for VAL (AI Planning plan validation and evaluation tools from KCL Planning department and the planning community around the ICAPS conference).
...morekarma-benchmark-reporter
lazd
A Karma benchmark reporter
vitest-evals
sentry-bot
End-to-end evaluation framework for AI agents, built on Vitest.
supplychain-firewall-benchmark-hello
rodrigopv
Benchmark package for testing SCA and repository firewall behavior. v1.0.0 is safe and prints "Hello World".
espression-rx
ianchi
ESpression extension to perform reactive evaluation of expressions
karma-benchmark-json-reporter
etpinard
A reporter for karma-benchmark outputting results to a JSON file
@tscircuit/autorouting-dataset-01
seveibar
A set of tscircuit problems to benchmark autorouting (currently 16 circuits in `lib/`).
deep-taxonomy-benchmark
jeswr
Generate the Deep Taxonomy Benchmark for testing RDF Reasoners
cali-cli
markoradak
Terminal calculator with real-time evaluation, currency conversion, and unit conversion
jiren
vk007
Jiren is a high-performance HTTP/HTTPS client, Faster than any other HTTP/HTTPS client.
@dapplion/benchmark
dapplion
Ensures that new code does not introduce performance regressions with CI. Tracks:
jkyy-evaluation
haotengfei
### 测评模块 SDK
log-lazy
konard
A lazy logging library with bitwise level control
eval2otel
evalops
Library to convert evaluation metrics and traces to OpenTelemetry GenAI semantic conventions
dream11-react-native-performance-tracker
wedesicooking
Benchmark React Native View Paint Time
probeai
k08200
CLI tool for testing and evaluating AI coding agents
ts-benchmark
mohammad-_-ahmad
A command line interface for monitoring the performance of typescript.
benny
caderek
A dead simple benchmarking framework
ppef
GitHub Actions
Portable Programmatic Evaluation Framework - Claim-driven, deterministic evaluation for experiments
js-index-data-structures
vhf
A benchmark of JS data structures suitable for in memory non unique indexing