200 open source apps like shoehorn, closest match first.
Kaldi Speech Recognition Toolkit
Create custom models, train easily
llama.ui
A minimal interface for AI Companion that runs entirely in your browser
Keras LLM Robot
A web UI Project In order to learn the large language model
LLM Axe
A simple, intuitive toolkit for quickly implementing LLM powered applications
Mnemo
Local-first AI memory layer for any LLM
Netron
Visualizer for neural network and machine learning models
GoModel
AI gateway written in Go with a unified OpenAI-compatible API
Llamastash
Zero-overhead, terminal-native local-LLM runtime manager
Devo
Model-neutral agent desktop/runtime for private, enterprise
Reins
Local AI chat for iPhone, iPad and Mac
Texts To Transformer
Train a tiny Transformer from scratch on your iMessage history
Webchat2api
OpenAI-compatible Web Chat API proxy
huggingface/hugging-face-jobs
Run compute jobs and Python scripts on HF infrastructure
Qwengate
Drop-in OpenAI-compatible API gateway for Qwen AI models
HacxGPT-Jailbreak-prompts
HacxGPT Jailbreak 🚀: Unlock the full potential of top AI models like…
Minimal LLM UI
Minimalistic UI for Ollama LMs - This powerful react interface for LLMs…
GPT Mobile
Chat app for Android that supports answers from multiple LLMs at once
liter-llm
Universal LLM API client — 163 providers, 14 native language bindings…
Icebreaker
A local AI chat app powered by Rust, iced, Hugging Face, and llama.cpp
Janas
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs…
overtchat
A simpler self-hosted alternative to Open WebUI
Tokentap
Intercept LLM API traffic and visualize token usage in a real-time terminal…
Web LLM
High-performance In-browser LLM Inference Engine
SourceWeft
Open-source, self-hostable alternative to ChatGPT and NotebookLM
Gemini-FastAPI
Web-based Gemini models wrapped into an OpenAI-compatible API
Generative AI With Langchain
Build production-ready LLM applications and advanced agents
Syrtis
AI token usage & quota monitor for the macOS menu bar
Coai
Next Gen Multi-tenant AI One-Stop Solution
DeepSeek MCP Server
Official DeepSeek MCP server for chat, completion, model listing
Kiln
Intuitive app to build your own AI models
AI-Flow
Connect multiple AI models easily
MLX Tune
Fine-tune LLMs on your Mac with Apple Silicon
Open Responses
Self-hosted alternative to OpenAI's Responses API compatible
Kaas
Cross-platform desktop LLM client for OpenAI ChatGPT, DeepSeek R1
OpenRouter Model Price Comparison
Compare pricing across different AI models available on OpenRouter
Daan
Lightweight LLM Client with MCP & Characters
Chatpassport
Move AI conversations between ChatGPT, Claude, Gemini, and DeepSeek
Qwen3 TTS Apple Silicon
Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4)
Chat0
Blazingly-fast open source AI chat app
OpenAgentCore
Open-source, self-hosted implementation of the OpenAI Agents API
Ollama
Load and run large LLMs locally to use in your terminal or build your apps
Nari Qwen3 TTS
Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second
Chat
chat web app for teams, sass with user management and ratelimit, support…
Alpaca
Local and online AI hub
MOVO
Turn DeepSeek Harness into a self-hosted enterprise Agent platform
Sherpa Onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement
Gerbil
A desktop app for running Large Language Models locally
Langkit
An open-source toolkit for monitoring Large Language Models (LLMs)
Slotstream
Run a 105 GB AI model on a Mac that can't hold it
Auto-Keras
Build, train, and deploy AI models effortlessly