Docket

Docket is an AI-powered QA testing platform that lets teams create, run, and manage end-to-end web tests with plain-language prompts; its AI agent visually interacts with apps in a real browser to simulate users, adapt to UI changes, and eliminate flaky selector-based tests. Use it to speed up test creation, increase coverage, catch bugs earlier, reduce maintenance, and enable nontechnical teammates to contribute to QA.

Yorph AI is an AI-powered data engineering platform that enables product managers and analysts to seamlessly connect and analyze multiple data sources through a conversational interface leveraging autonomous AI agents to automate and optimize data pipelines without code while giving users transparency and control with human-in-the-loop workflows and robust security features organizations choose Yorph AI to accelerate analytics eliminate technical bottlenecks and maintain strong governance and compliance making it especially valuable for teams needing fast reliable and explainable insights without dedicated data engineering resources

Klavis AI is an open source integration platform that uses advanced AI to let language models and autonomous agents reliably connect to thousands of external business tools and platforms at any scale making it ideal for enterprises and developers building AI-powered applications by abstracting away the complexities of authentication infrastructure and client library management Klavis AI streamlines secure integration with deep access to hundreds of functions per app enabling sophisticated agent workflows such as sales research across enterprise CRMs or communication platforms with minimal code its AI-focused Model Context Protocols ensure agents can interact programmatically with real-world data and workflows while offering prebuilt connectors SDKs and both hosted and self-hosted deployment options so teams can accelerate development reduce operational costs and empower their AI with robust real-world capabilities.

MemMachine is an open source AI memory layer that empowers AI agents to remember learn and adapt over time by storing and recalling information from previous interactions including user preferences goals and procedural knowledge AI plays a central role by enabling contextual understanding and personalized responses instead of generic stateless outputs making conversations more relevant and engaging MemMachine integrates seamlessly with leading large language models like OpenAI Claude Gemini and others and can be deployed on the cloud or on premise making it ideal for developers building intelligent agents and enterprises seeking scalable secure and compliant platforms With its unique persistent memory capabilities MemMachine transforms AI agents into context aware collaborators reduces repetition and manual input and builds long term trust and efficiency between users and AI

Kento is an AI semantic caching platform that reduces AI usage costs by up to 40% by identifying and storing repeated user queries. It sits between applications and AI models, serving cached responses instantly for duplicate or semantically similar prompts. This eliminates paying full rates for repeated questions, improving response speed and reducing API expenses. The system includes a dashboard that tracks prompts, spending, and savings, helping developers understand usage patterns. Integration requires only a single line of code, and it supports all major LLM providers with free and paid plans for scalable optimization.

Agenta is an open source platform that streamlines the development monitoring and evaluation of applications powered by large language models by leveraging AI to enable collaborative prompt engineering systematic prompt versioning robust A/B testing and in depth observability Agenta allows users to easily experiment with and compare outputs from over 50 LLMs track performance and costs integrate user feedback and conduct detailed tracing and debugging It supports frameworks like LangChain and LlamaIndex and even allows for testing with image inputs and advanced agent workflows making it ideal for engineers product teams and researchers who want to accelerate LLM app iteration ensure reliability and optimize model performance through seamless collaborative workflows and data driven insights.

AgentKit is a visual AI tool from OpenAI that lets users design build and manage advanced multi-step agent workflows without needing to code by arranging logic and actions on a simple drag and drop interface powered by state of the art AI models Agent Builder simplifies building complex automations with features like multi agent orchestration built in safety guardrails integration with popular apps and instant testing so teams across technical and non technical backgrounds can quickly prototype collaborate and deploy AI powered agents in products customer support and business processes making scalable and secure AI automation accessible for enterprises and startups