Lunary
Lunary is an AI developer platform designed to help AI teams manage, improve, and protect Large Language Model (LLM) chatbots. It offers features such as conversation and feedback tracking, analytics on costs and performance, debugging tools, and a prompt directory for versioning and team collaboration. Lunary supports integration with various LLMs and frameworks, including OpenAI and LangChain, and provides SDKs for Python and JavaScript. Guardrails to deflect malicious prompts and sensitive data leaks. Deploy in your VPC with Kubernetes or Docker. Allow your team to judge responses from your LLMs. Understand what languages your users are speaking. Experiment with prompts and LLM models. Search and filter anything in milliseconds. Receive notifications when agents are not performing as expected. Lunary's core platform is 100% open-source. Self-host or in the cloud, get started in minutes.
Learn more
Traccia
Traccia is an OpenTelemetry-native observability, governance, and policy enforcement platform for production AI agents. It gives engineering teams complete visibility into every LLM call, tool invocation, decision, token, and dollar spent across frameworks like LangChain, CrewAI, OpenAI Agents SDK, AutoGen, and LlamaIndex. Beyond tracing, Traccia helps organizations govern AI systems with runtime policies that can detect and block unsafe behavior, runaway costs, restricted model usage, and PII exposure before incidents reach production. Accurate cost attribution, agent health monitoring, a unified agent registry, and EU AI Act evidence generation make it suitable for enterprise deployments. With a lightweight open-source SDK and managed platform, Traccia enables teams to build, debug, monitor, and govern AI agents at scale without vendor lock-in, using standard OpenTelemetry instrumentation.
Learn more
Arize Phoenix
Phoenix is an open-source observability library designed for experimentation, evaluation, and troubleshooting. It allows AI engineers and data scientists to quickly visualize their data, evaluate performance, track down issues, and export data to improve. Phoenix is built by Arize AI, the company behind the industry-leading AI observability platform, and a set of core contributors. Phoenix works with OpenTelemetry and OpenInference instrumentation. The main Phoenix package is arize-phoenix. We offer several helper packages for specific use cases. Our semantic layer is to add LLM telemetry to OpenTelemetry. Automatically instrumenting popular packages. Phoenix's open-source library supports tracing for AI applications, via manual instrumentation or through integrations with LlamaIndex, Langchain, OpenAI, and others. LLM tracing records the paths taken by requests as they propagate through multiple steps or components of an LLM application.
Learn more
Plurai
Plurai is the real-world trust platform for AI agents, built for simulation-driven evaluation, protection, and optimization that turns agents into trusted, continuously improving production systems. It helps teams train evals and guardrails tailored to their use case, bridging the gap from prototype to reliable production at scale. Plurai’s simulation platform prepares agents for the real world, not the lab, with hyper-realistic, product-tailored experimentation and evaluation that covers production complexity. It generates authentic multi-turn scenarios, personas, required artifacts, and tool mocking, using organizational PRDs, relevant sources, and policies to build a knowledge graph and expand edge-case coverage. Instead of relying on static datasets, manual test creation, or inconsistent LLM-as-a-judge methods, Plurai groups evaluations into structured, runnable experiments so teams can test new versions, measure regressions, and validate improvements before release.
Learn more