Highlights
Lists (2)
Sort Name ascending (A-Z)
Starred repositories
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Browser automation CLI for AI agents
Expose local servers via tunnels. Supports WebSockets, SSE, password protection, Cloudflare CDN caching
Memory library for building stateful agents
hardware implementation of transformers running microgpt at 50k+ tkps
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
An elegant home server OS. Run OpenClaw, store your files and photos, run a Bitcoin node, and do more with over 300 apps in the Umbrel App Store.
Vane is an AI-powered answering engine.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
The open-source AI voice studio. Clone, dictate, create.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
Point at any URL/YouTube/Podcast or file. Get the gist. CLI and Chrome Extension.
Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity
Ultra-lightweight, zero dependency, semantic HTML, CSS, JS UI library. ~8KB min+gz.
Fast and streamable Excalidraw MCP App
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
High performance self-hosted photo and video management solution.
A free, open source, and extensible speech-to-text application that works completely offline.
🔥🔥🔥 Open-source Jira, Linear, Monday, and ClickUp alternative. Plane is a modern project management platform to manage tasks, sprints, docs, and triage.
🌤️ OpenCloud is the open source platform for file management, sharing and collaboration. Simple and sovereign.
Secure and fast microVMs for serverless computing.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Beads - A memory upgrade for your coding agent