xai-org/grok-build+2097 stars 24hREPO
msitarzewski/agency-agents+659 stars 24hREPO
safishamsi/graphify+599 stars 24hREPO
stablyai/orca+566 stars 24hREPO
jamiepine/voicebox+537 stars 24hNEWxai-org/grok-build+2097 stars 24hREPOmsitarzewski/agency-agents+659 stars 24hREPOsafishamsi/graphify+599 stars 24hREPOstablyai/orca+566 stars 24hREPOjamiepine/voicebox+537 stars 24hA local LLM is a language model that runs on your own machine or servers instead of a hosted API — for privacy, offline use, and cost control.
A local LLM runs inference on hardware you control. With quantization and efficient runtimes, capable open models now run on a laptop or a single GPU. Teams choose local for data privacy, offline operation, predictable cost, and no per-token API fees.
The open-source local-LLM ecosystem covers inference engines, model runners with one-command setup, and UIs — the layer that turns raw model weights into something you can actually chat with or build on.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
SGLang is a high-performance serving framework for large language models and multimodal models.
Local voice clone, video dubbing, dictation and audiobook maker. The open-source ElevenLabs alternative.
Hundreds of models & providers. One command to find what runs on your hardware.
