AI observability 7
All-in-one platform for production AI apps
Timbal is an end-to-end production AI platform for building, deploying, monitoring, evaluating, and governing AI agents, workflows, knowledge bases, and interfaces on the models you choose.
Open-source platform for designing, deploying, and monitoring AI workflows.
Draft'n run is an open-source AI agent platform that empowers teams to design, deploy, and monitor AI-powered features and production-ready AI workflows faster than ever. It transforms complex AI integration into an intuitive, visual process with full transparency, control, and scalability. The platform enables developers, product teams, and software and AI agencies to build production-ready AI workflows without code, including AI chatbots, automated workflows, and agentic AI, with built-in DevOps, observability, and governance. It features a drag-and-drop Studio for building workflows, an interactive Sandbox for testing, comprehensive Observability for monitoring, and REST APIs for integration.
LLM observability and prompt A/B testing platform.
Currai is an observability and tracing platform designed for LLM applications. It helps developers move away from basic print statement debugging by tracing every prompt, token, and tool call in a single view. The platform enables monitoring production traffic, calculating costs based on processed bytes, running evaluations, and A/B testing prompt versions live without requiring any local infrastructure to run. It offers drop-in Python and TypeScript SDKs and is byte-compatible with Langfuse and OpenTelemetry, making it easy to integrate or migrate existing projects.
End-to-end AI evaluation and observability platform for testing and deploying AI applications.
Maxim is an end-to-end AI evaluation & observability platform that helps you test and deploy AI apps with greater speed & confidence. Its developer stack includes tools for the full AI lifecycle: experimentation, pre-release testing, & post-release monitoring. It offers features like agent simulation and evaluation, prompt engineering tools, observability, and continuous quality monitoring. Maxim supports various AI frameworks and provides SDKs, CLI, and webhook support.
Data workspace and prompt engineering platform for AI product teams.
Latitude is a data workspace that helps analysts streamline their workflow and build interactive data apps quickly. It is also an end-to-end platform for prompt engineering where domain experts can collaborate with engineers to ship and maintain production-grade LLM features. Latitude is the open-source AI engineering platform for product teams to design prompts, evaluate and refine them using real data, and deploy new changes easily.
Llog: Collaborative analytics and insights tool for LLM interactions and monitoring.
Llog is a collaborative analytics and insights tool designed for LLMs. It logs end-user interactions with a single request and facilitates surfacing, sharing, and deriving insights from those logs with all business stakeholders. It's an end-to-end platform for teams to gain insights into their LLM applications post-production, offering a collaborative workspace for reviewing logs, flagging important items, and assigning tasks within the context of model outputs. Llog provides unlimited seats at any price tier and full visibility into end-user interactions, allowing users to understand what their LLM is actually saying. Insights are available within seconds using a simple API format.
Organizational intelligence platform for tracking, attributing, and improving company-wide AI workflows.
Oberhahn is an organizational intelligence platform that connects AI activity and costs across tools such as Claude Code, Codex, Cursor, Copilot, OpenAI, Anthropic, and internal agents to the projects, features, and issues they support. It helps organizations understand which AI workflows are effective, who created them, how they spread across teams, and what outcomes they produce. Oberhahn provides visibility, workflow attribution, intelligence, recommendations, and governance so companies can scale successful AI practices, reduce waste, and preserve organizational knowledge as models, tools, and employees change.
