evalship
evalship helps engineering teams test LLM-powered software with a review of their evals at setup and a report on every pull request. The review checks scorers, judges and prompts for flaws, such as a judge that scores 1.0 when its call fails, and gives each flaw a fix with code references. Setup is a prompt for your coding agent: it configures GitHub Actions and opens a setup pull request. On later pull requests, evalship compares results with the default branch, reports the evals a change really broke and the likely cause, sets flaky evals aside, and flags changed prompts or LLM calls that no eval exercises. Its check can block a merge that breaks an eval. It reads results from pytest, Vitest, Jest, promptfoo, Langfuse, Braintrust and LangSmith, with no SDK to add. Evals run in the customer's own GitHub Actions with their own model API keys; evalship only reads the results. Teams get a dashboard with each eval's history and a weekly report by email. Public repositories are free.
Learn more
Latitude
Latitude is an open-source prompt engineering platform designed to help product teams build, evaluate, and deploy AI models efficiently. It allows users to import and manage prompts at scale, refine them with real or synthetic data, and track the performance of AI models using LLM-as-judge or human-in-the-loop evaluations. With powerful tools for dataset management and automatic logging, Latitude simplifies the process of fine-tuning models and improving AI performance, making it an essential platform for businesses focused on deploying high-quality AI applications.
Learn more
LayerLens
LayerLens is an independent AI model evaluation platform for understanding how models perform through verified results across benchmarks, prompt-level results, agentic benchmarks, and audit-ready comparisons across vendors. It helps teams compare more than 200 AI models side by side, with transparent benchmarks, model comparison tools, and consistent evaluation methods for accuracy, latency, behavior, and real-world applicability. LayerLens is built for deep model analysis through Spaces, where teams can group benchmarks and evaluations, explore task strengths, and track performance patterns in context. It supports continuous evaluation by running ongoing evals across model versions, prompt changes, judge updates, and live traces, helping teams detect quality regressions, drift, silent failures, contamination, and policy issues before they affect production.
Learn more
ChainForge
ChainForge is an open-source visual programming environment designed for prompt engineering and large language model evaluation. It enables users to assess the robustness of prompts and text-generation models beyond anecdotal evidence. Simultaneously test prompt ideas and variations across multiple LLMs to identify the most effective combinations. Evaluate response quality across different prompts, models, and settings to select the optimal configuration for specific use cases. Set up evaluation metrics and visualize results across prompts, parameters, models, and settings, facilitating data-driven decision-making. Manage multiple conversations simultaneously, template follow-up messages, and inspect outputs at each turn to refine interactions. ChainForge supports various model providers, including OpenAI, HuggingFace, Anthropic, Google PaLM2, Azure OpenAI endpoints, and locally hosted models like Alpaca and Llama. Users can adjust model settings and utilize visualization nodes.
Learn more
