Awesome AI Agents › Stateful Serverless Frameworks
StackImpact Go Profiler is a production-grade performance profiling tool designed for Go applications, providing developers with continuous and historical insights into application performance. It helps identify CPU usage, memory allocation, blocking calls, latency bottlenecks, and errors, making it essential for optimizing and troubleshooting Go programs in both development and production environments. The profiler offers continuous hot spot profiling, latency bottleneck tracing, error and panic monitoring, and health monitoring of runtime metrics such as CPU, memory, and garbage collection. It also supports alerts on profile anomalies and team access for collaborative performance analysis. The profiler operates by importing the StackImpact agent into a Go program, which automatically starts and stops various sampling profilers. The collected data is periodically reported to the StackImpact Dashboard for visualization and analysis. The agent can also be used in manual mode for development purposes, allowing explicit control over profiling start and stop times. Configuration options include specifying an agent key, application name, version, environment, hostname, proxy settings, and logging preferences. StackImpact Go Profiler supports focused profiling for specific code segments, such as HTTP handlers, enabling precise profiling of relevant execution intervals with timing information. It also provides APIs for error and panic reporting, aggregating and reporting these events with stack traces to aid in debugging. Manual profiling is available but recommended only for short-lived programs, as automatic profiling is preferred for production use. The profiler is compatible with Linux, OS X, and Windows, requiring Go version 1.5 or higher. It is designed to have minimal overhead, measured to be less than 1% under high load, ensuring it does not significantly impact application performance. The StackImpact Dashboard offers a comprehensive interface for analyzing performance data, including CPU, memory, I/O hot spots, execution bottlenecks, and process metrics. Overall, StackImpact Go Profiler is a robust and feature-rich tool for Go developers seeking to monitor, analyze, and optimize application performance with detailed profiling and error monitoring capabilities.
https://github.com/stackimpact/stackimpact-go
LiteLLM is a Python SDK and proxy server that provides a unified OpenAI-compatible interface to call over 100 large language model APIs from multiple providers, featuring consistent output, retry logic, budget controls, and extensive observability integrations.
Flowise is an open-source drag-and-drop platform that enables users to easily build and deploy customized Large Language Model (LLM) application workflows with a user-friendly interface and flexible deployment options.
Parlant is a Conversation Modeling engine that enables precise, consistent, and reliable control over GenAI-driven conversational agents by enforcing structured behavioral guidelines and adapting dynamically to user interactions.
ToolBench is an open platform for training, serving, and evaluating large language models with advanced tool-use capabilities using a large-scale, richly annotated dataset of real-world APIs.
RivetKit is a stateful serverless framework that enables building scalable, real-time, and collaborative applications deployable across multiple platforms including Rivet, Cloudflare Workers, Bun, and Node.js.
LlamaDeploy is an async-first framework that enables seamless deployment, scaling, and productionization of agentic multi-service workflows built with llama_index, facilitating easy transition from development to cloud-based production environments.
Ragbits is a modular framework providing building blocks for rapid development, deployment, and monitoring of scalable and reliable Generative AI applications with flexible LLM integration and advanced document processing capabilities.
Mirascope is a flexible and user-friendly library that provides a unified interface to work with multiple large language model providers, simplifying AI-driven text generation and information extraction tasks.