Awesome GitHub RepositoriesTrace Format Normalization

Arize Phoenix is an LLM observability platform and evaluation framework designed to capture execution traces and monitor large language model applications. It serves as a prompt management system for versioning and testing templates, and as a self-hosted AI operations infrastructure for managing telemetry and experiments. The platform differentiates itself through a specialized embedding visualization tool used to detect data drift and optimize vector search. It provides a comprehensive evaluation suite that utilizes judge-based evaluators and ground-truth datasets to score model outputs, and

Speedscope is a web-based performance profiler that visualizes profiling data through interactive flamegraphs and timeline views. It ingests performance profiles from a wide range of sources, including Chrome, Firefox, Safari, Node.js, .NET Core, Instruments, Hermes, GHC, and Ruby, normalizing them into a common schema for unified analysis. The tool distinguishes itself with a canvas-based rendering engine that draws flamegraphs without DOM nodes for each frame, and a WebAssembly-based rendering pipeline for high-performance drawing. It offers left-heavy stack sorting to surface the most time

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

Perfetto is a platform for system-level performance tracing and analysis on Linux and Android. It combines a high-throughput trace recorder, a SQL-based query engine, and a browser-based visualizer into a single toolchain. The platform covers CPU scheduling and call-stack profiling, native and Java heap memory allocation tracking, GPU and graphics events, and system-wide counters such as CPU frequency and power consumption. The architecture decouples trace recording from offline analysis, using a compact protobuf format for event encoding and columnar storage for efficient SQL queries. The we

Plano is an AI agent orchestrator and LLM gateway proxy that unifies access to multiple AI providers through a single interoperable interface. It functions as a model routing engine that decouples applications from specific vendors using semantic aliases, allowing traffic to be shifted between providers without modifying application code. The system distinguishes itself with intent-based agent routing, which directs prompts to specialized agents based on semantic analysis. It features an interceptor-based filter chain system that acts as guardrail middleware to enforce safety policies, rewrit

AIClient-2-API is an AI gateway and proxy server that translates diverse large language model interfaces into a single standardized API format. It functions as an OpenAI API compatible proxy and multi-provider orchestrator, allowing a single client to interact with multiple different model backends through a unified interface. The project distinguishes itself by acting as a load balancer that distributes requests across multiple provider accounts using health checks and polling to bypass quota limits. It includes a TLS fingerprint emulator to simulate browser characteristics and prevent API a

This project is an AI API gateway and proxy that translates and normalizes requests between different AI model formats to ensure compatibility across client applications. It functions as a middleware service that can transform local command-line binaries into web services, allowing them to be triggered via HTTP requests. The system is distinguished by its ability to route multimodal text and image inputs and extract internal reasoning chains from model outputs to separate the chain of thought from the final answer. It includes an authentication manager that automatically cycles through multip

This library provides a structured framework for managing runtime failures and debugging within PHP applications. It functions by intercepting native language errors, warnings, and system signals, converting them into catchable, object-oriented exceptions to ensure consistent control flow throughout the application lifecycle. The project distinguishes itself by normalizing raw execution backtraces and providing a transformation layer that standardizes how system failures are reported. It includes specialized tools for monitoring the class loading process, ensuring that dependency resolution i