Stars
An automated document analyzer for Paperless-ngx using OpenAI API, Ollama, Deepseek-r1, Azure and all OpenAI API compatible Services to automatically analyze and tag your documents.
Personal ZMK firmware configuration for various boards (34-keys, Glove80, Planck)
OpenShell is the safe, private runtime for autonomous AI agents.
Hundreds of models & providers. One command to find what runs 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.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
An open-source compact CoreXY 3D printer designed for small apartments.
High-Quality Voice Cloning TTS for 600+ Languages
A collection of agent skills for CAD, robotics and hardware design
Gridfinity-compatible baseplate generator with puzzle connectors
Generate custom gridfinity bins with AI, from photos of your tools
Generate Parametric Gridfinity Bins and Baseplates in FreeCAD and build from them.
A ground-up rebuild of the stock gridfinity bins in OpenSCAD
Native and Compact Structured Latents for 3D Generation
Memory library for building stateful agents
The agent that grows with you
Slimmed, cleaned and fine-tuned oh-my-opencode fork, consumes much less tokens
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
No-as-a-Service (NaaS) is a simple API that returns a random rejection reason. Use it when you need a realistic excuse, a fun “no,” or want to simulate being turned down in style.
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
Fresh builds of llama.cpp with AMD ROCm™ 7 acceleration
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
Detailed visual + nutritional data for over 5,000 plates of food.
The open agent skills tool - npx skills
Lightweight, open-source AI agent for your tools, chats, and workflows.
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.