Local AI & Model Runners
Desktop model runners, local inference engines, and model management
Showing 1-20 of 62 projects
open-webui/open-webui
Self-hosted AI platform with Ollama and OpenAI API support
Comfy-Org/ComfyUI
Visual AI engine for designing and executing advanced diffusion pipelines with a node-based interface.
ggml-org/llama.cpp
Run LLMs locally in C/C++ with high performance
nomic-ai/gpt4all
Run local LLMs on any device with GPT4All
meta-llama/llama
Llama 2 inference code for running Llama models
zylon-ai/private-gpt
PrivateGPT enables private document interaction with GPT without data leaks.
FoundationAgents/OpenManus
OpenManus is a Python-based AI coding agent for building and managing models.
xai-org/grok-1
Open-source Grok-1 model for local inference with JAX
lllyasviel/Fooocus
Offline AI image generation with minimal user input
run-llama/llama_index
LLamaIndex framework for building LLM-powered agents
oobabooga/text-generation-webui
Web UI for local AI with multiple backends and offline capabilities
mudler/LocalAI
Self-hosted, open-source AI alternative to OpenAI with local LLM inference, no GPU required
exo-explore/exo
Run frontier AI models locally across devices using RDMA and tensor parallelism
zai-org/ChatGLM-6B
ChatGLM-6B is an open-source bilingual dialogue language model with 6.2B parameters, optimized for Chinese and English conversations.
janhq/jan
Open-source ChatGPT replacement with local AI model support
code-yeongyu/oh-my-opencode
A comprehensive AI agent harness for vibe coders
google/langextract
Extracts structured info from text using LLMs with source grounding
lib-pku/libpku
lib-pku/libpku: A collection of course materials and resources for vibe coders.
thedotmack/claude-mem
Claude Code plugin for AI-powered code capture and context injection
block/goose
Extensible AI agent for code suggestions, execution, and testing with LLM
Stay in the loop
Get weekly updates on trending AI coding tools and projects.