Trending / tags
llm
GitHub Trending repositories tagged with llm.
- 1diegosouzapw/OmniRouteOmniRoute is a TypeScript AI gateway that puts hundreds of model providers behind one endpoint. It targets coding assistants and agent tools such as Claude Code, Codex, Cursor, OpenCode, Cline, and Copilot, with quota-aware fallback across free and paid providers. The project also includes token compression, MCP and A2A support, plus desktop and PWA clients for managing model access.
- 2alibaba/open-code-reviewOpen Code Review is a Go-based CLI for AI-assisted code review, released by Alibaba and used at large scale. It combines deterministic review pipelines with an LLM agent, adds precise line-level comments, and includes tuned checks for issues such as null pointer errors, thread safety bugs, XSS, and SQL injection. It works with OpenAI and Anthropic compatible models, making it useful for teams that want automated review inside existing workflows.
- 3PrismML-Eng/Bonsai-demoBonsai-demo provides scripts and documentation for running PrismML's Bonsai language models locally across Mac, Linux, Windows, and CPU-only setups. It supports Metal, CUDA, Vulkan, and ROCm backends, with links to Bonsai 27B, 1-bit Bonsai, and Ternary-Bonsai model releases and whitepapers. The repo targets users who want to test compact or quantized LLMs on local hardware.
- 4earendil-works/piPi is a TypeScript toolkit for building AI agents, with a unified LLM API, agent runtime, terminal UI, and an interactive coding agent CLI. The project packages its core agent loop separately from its coding interface, making it useful for developers who want to experiment with agent workflows, automate coding tasks, or embed model-driven behavior into developer tools.
- 5Shubhamsaboo/awesome-llm-appsawesome-llm-apps is a large Python collection of open-source LLM application templates, including AI agents, agent skills, and RAG apps. The repository includes tested examples for Claude, Gemini, GPT, DeepSeek, Llama, Qwen, and other models, with Apache-2.0 licensing for reuse. It is useful for developers who want practical starter projects for building, adapting, or shipping LLM-powered products.
- 6kvcache-ai/ktransformersKTransformers is a Python framework for experimenting with efficient large language model inference and fine-tuning across CPU and GPU resources. It focuses on heterogeneous computing, letting researchers and engineers test optimization strategies for serving and adapting LLMs with different hardware layouts. The project targets practical inference, supervised fine-tuning, and future performance work for large models.