Results for “python sdk”

• Pydantic AIby PydanticOpen source Python framework for typed AI agents with validation and durable runsFreemiumWatch
• Grafana Cloud Agent Observabilityby Grafana LabsMonitor, evaluate, and improve production LLM agents in Grafana CloudFreemiumWatch
• Sentry Agent Tracingby SentryTraces AI agent runs and LLM calls inside Sentry application monitoringFreemiumWatch
• Pydantic Logfireby PydanticFull-stack observability and evaluation for AI appsFreemiumWatch
• Agent Observability (Datadog LLM Observability)by DatadogEvaluate, improve, and trace AI agents in one Datadog platformFreemiumWatch
• Agnoby AgnoPlatform for building, running and managing self-hosted AI agentsFreemiumWatch
• LangWatchby LangWatchAgent observability, simulation and evaluation platform for AI teamsFreemiumWatch
• HoneyHiveby HoneyhiveAgent observability and evaluation platform for tracing, scoring, and improving AI agents.FreemiumWatch
• Galileoby GalileoObservability, evaluation, and guardrails for LLM and agentic applications.UnknownWatch
• Braintrustby BraintrustAgent observability and evals for engineering and product teamsFreemiumWatch
• LangSmithby LangChainTrace, monitor and evaluate AI agents in productionFreemiumWatch
• Langfuseby LangfuseYC W23Open-source platform for tracing, evaluating, and improving LLM and agent applicationsFreemiumWatch
• Prefactorby PrefactorEvaluate live agent runs and intervene when actions need reviewFreemiumWatch
• Lunaryby LunaryMonitor LLM applications, review conversations and improve prompts$20+/user/moWatch
• PromptLayerby PromptLayerPrompt management, evals, and observability for AI teamsFreemiumWatch
• OpenHandsby OpenHandsOpen-source platform for running coding agents on engineering workFreemiumWatch
• Firebase AI Logicby GoogleCall Gemini models directly from mobile and web apps via FirebasePay as you goWatch
• AI Gatewayby VercelOne API key to route requests to 400+ AI models with fallbacks and spend trackingPay as you goWatch
• LangChainby LangChainOpen source framework for building agents that work with many models and toolsFreeWatch
• Amazon Bedrock AgentCoreby AmazonManaged AWS platform for building, running and governing AI agentsPay as you goWatch
• Evidently AIby Evidently AIYC S21Open-source AI evaluation and observability for LLMs and ML modelsUnknownWatch
• Confident AIby Confident AIYC W25AI quality platform for evaluating, tracing, and monitoring LLM applications across teams.FreemiumWatch

That’s all 22 tools.