#mistral

LearningCircuit/local-deep-research

Python

88

health

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

linkedin/Liger-Kernel

Python

88

health

Efficient Triton Kernels for LLM Training

lemonade-sdk/lemonade

C++

87

health

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

crmne/ruby_llm

Ruby

80

health

One beautiful Ruby API for OpenAI, Anthropic, Gemini, Bedrock, Azure, OpenRouter, DeepSeek, Ollama, VertexAI, Perplexity, Mistral, xAI, GPUStack & OpenAI compatible APIs. Agents, Chat, Vision, Audio, PDF, Images, Embeddings, Tools, Streaming & Rails integration.

NVIDIA-NeMo/Automodel

Python

79

health

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support