Search Results for "test"
Sort By:
Showing 279 open source projects for "test"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
1
GoogleTest
Google Testing and Mocking Framework
...Since they were so closely related, they were merged to create an even better GoogleTest. GoogleTest features an xUnit test framework, a rich set of assertions, user-defined assertions, death tests, among many others. It's been used on a variety of platforms, including Cygwin, Symbian, MinGW and PlatformIO. -
2
Micro Agent
AI CLI agent that writes code by iterating until tests pass
Micro Agent is a command-line tool designed to generate and refine code using a test-driven approach powered by large language models. Instead of producing one-shot code outputs, it creates or uses test cases and repeatedly iterates on the generated code until those tests pass successfully. This workflow emphasizes reliability by using structured feedback from failing tests to guide improvements, reducing the need for manual debugging and iteration. -
3
Empirical
Test and evaluate LLMs and model configurations
Empirical is the fastest way to test different LLMs and model configurations, across all the scenarios that matter for your application. -
4
TTRL
Test-Time Reinforcement Learning
TTRL is an open-source framework for test-time reinforcement learning in large language models, with a particular focus on reasoning tasks where ground-truth labels are not available during inference. The project addresses the problem of how to generate useful reward signals from unlabeled test-time data, and its central insight is that common test-time scaling practices such as majority voting can be repurposed into reward estimates for online reinforcement learning. ... -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
Ragas
Supercharge Your LLM Application Evaluations
Objective metrics, intelligent test generation, and data-driven insights for LLM apps. Ragas is your ultimate toolkit for evaluating and optimizing Large Language Model (LLM) applications. Say goodbye to time-consuming, subjective assessments and hello to data-driven, efficient evaluation workflows. Don't have a test dataset ready? We also do production-aligned test set generation. -
6
Ludwig
A codeless platform to train and test deep learning models
Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code. All you need to provide is a CSV file containing your data, a list of columns to use as inputs, and a list of columns to use as outputs, Ludwig will do the rest. Simple commands can be used to train models both locally and in a distributed way, and to use them to predict on new data. -
7
Qodo Cover
AI tool that generates tests to improve code coverage quickly
...It supports scanning entire repositories to automatically detect test files, gather relevant context, and extend test suites accordingly. -
8
CodiumAI Cover-Agent
CodiumAI Cover-Agent: An AI-Powered Tool for Automated Test Generation
CodiumAI Cover Agent aims to help efficiently increasing code coverage, by automatically generating qualified tests to enhance existing test suites. -
9
Opik
Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI
...Run experiments with different prompts and evaluate against a test set. Choose and run pre-configured evaluation metrics or define your own with our convenient SDK library. Consult built-in LLM judges for complex issues like hallucination detection, factuality, and moderation. -
Earn up to 16% annual interest with Nexo.Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
10
Groq Desktop
Local Groq Desktop chat app with MCP support
...The app is built with modern web technologies and packaged for native distribution, making it accessible even to non-developer users who just want to experiment with Groq models without writing code. Developers can also use groq-desktop-beta as a lightweight interface to test prompts, media inputs, or function-calling capabilities before embedding them into larger projects. The project offers installable builds (including via Homebrew on macOS) and supports easy setup, giving quick access to Groq’s inference services without needing to spin up a full backend. -
11
Goose
AI coding agent that's more than suggestions - install, execute, edit+
Goose is an open-source, extensible AI agent that enhances the software development process by going beyond traditional code suggestions. It allows developers to install, execute, edit, and test code with any large language model (LLM), facilitating a more efficient and streamlined workflow. Designed to operate locally within a developer's environment, Goose integrates seamlessly with various tools and platforms, providing a customizable and powerful assistant for coding tasks. Its architecture supports extensibility, enabling users to tailor the agent to their specific needs and preferences. ... -
12
promptfoo
Evaluate and compare LLM outputs, catch regressions, improve prompts
...Use built-in metrics, LLM-graded evals, or define your own custom metrics. Compare prompts and model outputs side-by-side, or integrate the library into your existing test/CI workflow. Use OpenAI, Anthropic, and open-source models like Llama and Vicuna, or integrate custom API providers for any LLM API. -
13
OpenClaw Installer
ClawdBot one-click deployment tool
...It supports multiple platforms, including macOS, Linux distributions (Ubuntu, Debian, CentOS), and Windows environments via compatible shells, and simplifies otherwise complex installation steps into a guided, terminal-based experience. The tool also includes options to test API connections, validate channel integrations like Telegram or Discord bots, and launch persistent services that keep OpenClaw running in the background. -
14
Kheish
Kheish: A multi-role LLM agent for tasks like code auditing
Kheish is a framework designed for cybersecurity professionals to automate penetration testing tasks, providing tools to streamline security assessments. -
15
Superpowers
An agentic skills framework & software development methodology
Superpowers Framework is a widely-used agentic skills framework and methodology for software development that equips coding agents like Claude Code with structured capabilities to plan, develop, test, and review code systematically. Instead of simply generating code, Superpowers drives an AI through a thoughtful software engineering workflow that starts with clarifying project intent, teasing out a detailed specification, and creating an implementation plan that is readable and actionable. It incorporates test-driven development, task planning, and sub-agent orchestration so that each engineering task is executed, checked, and iterated upon with rigor rather than ad-hoc improvisation. ... -
16
Nestia
NestJS Helper + AI Chatbot Development
...One of its defining advantages is its focus on performance optimization, offering dramatically faster runtime validation and serialization compared to traditional libraries commonly used in NestJS environments. Nestia also integrates advanced capabilities such as automatic end-to-end test generation and mock server simulation, allowing developers to test and prototype applications with minimal manual setup. -
17
FuzzyAI Fuzzer
A powerful tool for automated LLM fuzzing
...The framework can be integrated into development pipelines to continuously test AI APIs and detect weaknesses before deployment. FuzzyAI provides testing tools, datasets, and evaluation workflows that help researchers measure how well models resist harmful instructions or attempts to bypass safety mechanisms. -
18
GitHub Copilot CLI
GitHub Copilot CLI brings the power of Copilot coding agent
GitHub Copilot CLI is a command-line interface tool. It brings AI-powered coding assistance directly into your terminal. GitHub Copilot CLI allows you to build, debug, refactor, and understand code via natural language conversations. You can have these conversations within the Active Directory. It integrates tightly with your GitHub context—repositories, issues, pull requests. The Copilot can leverage repository context when making suggestions. The tool is currently in public preview and is... -
19
Jovo Framework
The React for Voice and Chat, build apps for Alexa, Google Assistant
...The Jovo Debugger and Test Suite enable you to build robust experiences that behave exactly how you want them to. The Jovo CLI makes it possible to deploy your project to different environments using stage specific configurations. -
20
XcodeBuildMCP
A Model Context Protocol (MCP) server
XcodeBuildMCP is a Model Context Protocol server that exposes Xcode operations as typed tools and resources so AI assistants can build, test, and debug iOS apps programmatically. It’s organized with a modern plugin architecture and workflow-scoped tool directories, covering common developer actions across projects, schemes, targets, simulators, real devices, and Swift packages. The server aims to be “agent-ready,” surfacing capabilities (build, clean, test, archive, install, run, log collection) with explicit schemas instead of brittle prompt instructions. ... -
21
PML
The easiest way to use deep metric learning in your application
This library contains 9 modules, each of which can be used independently within your existing codebase, or combined together for a complete train/test workflow. To compute the loss in your training loop, pass in the embeddings computed by your model, and the corresponding labels. The embeddings should have size (N, embedding_size), and the labels should have size (N), where N is the batch size. The TripletMarginLoss computes all possible triplets within the batch, based on the labels you pass into it. ... -
22
Easy DataSet
A powerful tool for creating datasets for LLM fine-tuning
...The system includes automated question-generation capabilities, hierarchical label trees, and answer generation pipelines that use LLM APIs to produce coherent paired data with customizable templates. Beyond dataset creation, Easy-dataset also provides a built-in evaluation system with model testing and blind-test features, helping teams validate model performance using curated test sets. -
23
FullTClash
General proxy performance testing tool based on Clash using Telegram
...The front end part uses Telegram API as the interactive interface, which needs to be used in conjunction with Telegram, that is, a Telegram robot (bot), FullTClash bot is a Telegram robot (hereinafter referred to as bot) carrying its test tasks. -
24
Freqtrade
Free, open source crypto trading bot
Freqtrade is a free and open-source crypto trading bot written in Python. It is designed to support all major exchanges and be controlled via Telegram or WebUI. It contains backtesting, plotting, and money management tools as well as strategy optimization by machine learning. Always start by running a trading bot in Dry-run and do not engage money before you understand how it works and what profit/loss you should expect. We strongly recommend you have basic coding skills and Python... -
25
Langflow
Low-code app builder for RAG and multi-agent AI applications
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
