Portable installation OpenwebUI & llama.cpp

Xiaomi MiMo V2.6: Qwen 9B Updated Coding Agent on 3GB VRAM! - Distilled 9B model for fast offline automation

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted …

Needle 3: This AI Is Only 29MB — Yet It Can Control Your Devices Offline!

Run Claude Code on Google Gemini (or DeepSeek/Qwen/GPT-OSS) via Vertex AI, billed to a Google Cloud $300 credit — patched claude-code-router setup

Generate AI videos with Google Veo 3 — free on your $300 Google Cloud credit — from Claude Code (chat skill) or a bundled Higgsfield-style web UI. Your own Google login, no third-party API keys, no…

Secure macOS setup, testing, and rollback for GPT-6 Astra through AgentRouter in Codex desktop.

Your own JARVIS: a local voice + memory-graph HUD driven by Claude Code, speaking through Fish Audio. Runs on your Claude subscription, memory is a folder of markdown.

MediaExplorer is a hobby browser for Windows 10 Mobile (W10M, build 15063+) built without the system WebView or Chakra engine. It uses a custom HTML parser, CSS engine with selectors/cascade/flexbo…

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Local AI inference server for LLMs and other models, forked from:

Can I Run AI

XBSX2 UWP/WinRT - The PlayStation 2 Emulator for Xbox Series/Xbox One

Put the world's best AI agents to work. One workspace for all of them -- Claude Code, Codex, Gemini, Grok and more, running side by side on your Desktop.

K2 Horizon: This Tiny 0.9B AI Runs on Smartwatches! (Local Setup) - Offline DSA Coach and 128K STEM Textbook Q&A interface powered by IFM/K2-Horizon-0.9B.

Chromium extension that routes AI services through your own proxy. Bypass geo-restrictions for Gemini, AI Studio, Google Labs, ChatGPT, Claude, YouTube and others.

Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.

Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized m…

Ouroboros With Love — a Telegram-native fork of the original Ouroboros, preserving its self-creating spirit while adding multi-user mode and OpenAI support.

A curated list of awesome resources, tools, and tutorials for OpenAI Codex CLI

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

A curated, continuously updated reading list of 500+ papers on LLM agents: planning, memory, tool use, multi-agent, evaluation & safety. Companion to the survey 'LLM Agents: A Survey'.

Turn a ChatGPT subscription into a local OpenAI-compatible API - a frontier-model brain for any agent framework. Tool calling, vision, streaming, multi-account quota failover, llama.cpp local-model…

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

Quake III port for AuroraOS with GLES3 support.

A WinRT based client for use with a Synapse server configured with mautrix bridges

WinUI: a modern UI framework with a rich set of controls and styles to build dynamic and high-performing Windows applications.

Windows Device Image Generator，用于生成wcos/wp镜像的辅助工具