Showing 6 results in LLM Ops & Observability
LiteLLM
Unified gateway for 100+ LLMs with spend tracking
LiteLLM is a Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI format, with cost tracking, guardrails, loadbalancing and logging. Supports Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM.
Langfuse
LLM engineering platform — tracing, prompt management, cost tracking.
MIT-licensed alternative to LangSmith. Full observability for LLM chains, version-controlled prompts, A/B testing, and dataset evaluation.
Helicone
LLM observability and AI gateway — one-line integration for logging, cost tracking, prompt management, and rate limiting
Build reliable AI apps with comprehensive observability
Laminar
Agent observability and evaluation platform — signal alerts, trace debugging, and automated evals for LLM products
Open-source LLM observability platform — trace debugging, signal alerts, and automated evaluations for AI products. Alternative to LangSmith and Helicone.
OpenLIT
OpenTelemetry-native LLM observability — tracing, evaluation, prompt management, and cost tracking
Monitor, debug, and scale LLM applications with ease
Proxed AI
Secure AI API management for iOS apps with DeviceCheck
Proxed.AI is a secure proxy backend for iOS apps that protects your AI API keys and controls AI responses. Uses Apple DeviceCheck to lock down API keys and provides a visual schema builder to structure AI outputs.