Code/llm

github.com

Cherry Studio is an AI productivity tool that supports multiple LLM providers, enhancing collaboration and efficiency for users across platforms.

github.com

Helicone is an open-source LLM observability platform that enables AI engineers to monitor and evaluate models efficiently.

github.com

Lucebox is a hub for optimized LLM inference tailored for specific consumer hardware, enhancing AI performance and efficiency.

github.com

Textgen is a local LLM interface for text and image generation, ensuring privacy and ease of use.

github.com

oMLX is an LLM inference server optimized for Apple Silicon, enabling efficient model management from the macOS menu bar.

github.com

A framework for building multi-agent workflows using OpenAI's technology.

github.com

SGLang is an open-source framework for efficient serving of large language and multimodal models, ensuring low-latency and high-throughput performance.

github.com

LangAlpha is an AI investment agent that enhances financial research and decision-making through persistent workspaces and advanced data analysis.

github.com

vLLM is an efficient engine for LLM inference and serving, designed for high throughput and memory management.

github.com

OmniRoute is an AI gateway that provides a unified API for accessing multiple AI models, ensuring cost-effective and reliable usage.