Fast Inference | Fast hosted models, one API
Run high-throughput open models through one OpenAI-compatible API, with transparent pricing, project-scoped keys, and built-in usage analytics.
DevPass by LLM Gateway - All-Access Dev Plans for AI Coding
One subscription, every coding model. Fixed-price dev plans for Claude Code, Cursor, and 200+ models.
Desert Ant Labs: On-device AI models and SDKs
Desert Ant Labs is a frontier AI lab for on-device models. Specialized models that run on Apple, Android, and the web, dropped into any product in a few lines of native code.
Experiential Labs · The open source AI gateway
Source-code: https://github.com/experientiallabs/experiential
Waku — one native app for all your coding agents
Source-code: https://github.com/egoist/waku
mlx-optiq · Run LLMs locally on your Mac
Open-source: https://pypi.org/project/mlx-optiq/
Modal: High-performance AI infrastructure
Bring your own code, and run CPU, GPU, and data-intensive compute at scale. The serverless platform for AI and data teams.
E2B | The Enterprise AI Agent Cloud
E2B Gives AI Agents Secure Computers with Real-World Tools. E2B is Used by 94% of Fortune 100 Companies for Frontier Agentic Workflows.
Daytona - Secure Infrastructure for Running AI-Generated Code
Deploy Al code with confidence using Daytona's lightning-fast infrastructure. 90ms environment creation,
stateful operations, and enterprise-grade security.
drumih/turbo-fieldfare · GitHub
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook - drumih/turbo-fieldfare
OmniRoute — Free AI Gateway for Multi-Provider LLMs
Source-code: https://github.com/diegosouzapw/OmniRoute
9Router - Free AI Router | Smart Fallback for Claude, Codex & More
Source-code: https://github.com/decolua/9router
lyogavin/airllm: AirLLM 70B inference with single 4GB GPU · GitHub
AirLLM 70B inference with single 4GB GPU
ayushh0110/ScreenMind: AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.
AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private. - ayushh0110/ScreenMind
Local Waifu | A self-learning AI companion for macOS
A self-learning AI companion that lives on your Mac. She remembers you, listens, learns who you are. No cloud, no subscription. $25 once, 7 days free.
Andyyyy64/whichllm: Find the local LLM that actually runs and performs best on your hardware
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
Locally AI - Run AI models locally on your iPhone, iPad, and Mac
Run Llama, Gemma, Qwen, DeepSeek, and more on your iPhone, iPad, and Mac. Optimized for Apple Silicon. Offline. Private.
Odysseus — A Self-Hosted AI Workspace
Source-code: https://github.com/odysseus-dev/odysseus
Cotabby - local AI autocomplete for macOS
Source-code: https://github.com/FuJacob/cotabby
Sim — The AI Workspace | Build, Deploy & Manage AI Agents
Source-code: https://github.com/simstudioai/sim
Caveman — the token-efficient stack for agent-native builders
Source-code: https://github.com/juliusbrussee/caveman
mozilla-ai/llamafile: Distribute and run LLMs with a single file. · GitHub
Distribute and run LLMs with a single file
LocalAI – Offline AI Chat LLM - Apps on Google Play
Run powerful open-source AI models offline. Private chat, images, docs.
LLM Hub – 15+ Private AI Models on Android, Free
Source-code: https://github.com/timmyy123/LLM-Hub