Pezzo
Pezzo is the open-source LLMOps platform built for developers and teams. In just two lines of code, you can seamlessly troubleshoot and monitor your AI operations, collaborate and manage your prompts in one place, and instantly deploy changes to any environment.
Learn more
PromptHub
Test, collaborate, version, and deploy prompts, from a single place, with PromptHub. Put an end to continuous copy and pasting and utilize variables to simplify prompt creation. Say goodbye to spreadsheets, and easily compare outputs side-by-side when tweaking prompts. Bring your datasets and test prompts at scale with batch testing. Make sure your prompts are consistent by testing with different models, variables, and parameters. Stream two conversations and test different models, system messages, or chat templates. Commit prompts, create branches, and collaborate seamlessly. We detect prompt changes, so you can focus on outputs. Review changes as a team, approve new versions, and keep everyone on the same page. Easily monitor requests, costs, and latencies. PromptHub makes it easy to test, version, and collaborate on prompts with your team. Our GitHub-style versioning and collaboration makes it easy to iterate your prompts with your team, and store them in one place.
Learn more
HoneyHive
AI engineering doesn't have to be a black box. Get full visibility with tools for tracing, evaluation, prompt management, and more. HoneyHive is an AI observability and evaluation platform designed to assist teams in building reliable generative AI applications. It offers tools for evaluating, testing, and monitoring AI models, enabling engineers, product managers, and domain experts to collaborate effectively. Measure quality over large test suites to identify improvements and regressions with each iteration. Track usage, feedback, and quality at scale, facilitating the identification of issues and driving continuous improvements. HoneyHive supports integration with various model providers and frameworks, offering flexibility and scalability to meet diverse organizational needs. It is suitable for teams aiming to ensure the quality and performance of their AI agents, providing a unified platform for evaluation, monitoring, and prompt management.
Learn more
Weavel
Meet Ape, the first AI prompt engineer. Equipped with tracing, dataset curation, batch testing, and evals. Ape achieves an impressive 93% on the GSM8K benchmark, surpassing both DSPy (86%) and base LLMs (70%). Continuously optimize prompts using real-world data. Prevent performance regression with CI/CD integration. Human-in-the-loop with scoring and feedback. Ape works with the Weavel SDK to automatically log and add LLM generations to your dataset as you use your application. This enables seamless integration and continuous improvement specific to your use case. Ape auto-generates evaluation code and uses LLMs as impartial judges for complex tasks, streamlining your assessment process and ensuring accurate, nuanced performance metrics. Ape is reliable, as it works with your guidance and feedback. Feed in scores and tips to help Ape improve. Equipped with logging, testing, and evaluation for LLM applications.
Learn more
