Lists (5)
Sort Name ascending (A-Z)
Stars
Nanbeige 4.3 33B llama.cpp setup and benchmark notes
A Claude skill that turns vibecoded, AI-looking UI into a designed interface
yoink any video from your terminal. no shady ads.
Per-user Cloudflare Quick Tunnel system service and Linux tray indicator
ArtCraft is an intentional crafting engine for artists, designers, and filmmakers
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
Reverse engineer anything with agents, from app behavior down to native binaries.
The cryptography-based networking stack for building unstoppable networks with LoRa, Packet Radio, WiFi and everything in between.
basic implementation of distributed private tracker like file seed / leech
a truly censorship-resistant alternative to Twitter that has a chance of working
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
jmagly / ollama-unify
Forked from robit-man/ollama-unifyConsolidate scattered Ollama model stores into one canonical location — interactively, safely, and at full hardware speed.
COM-guided Dropbear humanoid locomotion in NVIDIA Isaac Lab with RSL-RL PPO, live viewer, robot USD, and validated checkpoints
A network for everyone currently in the corporate-overlord inference cuck chair in the corner of the motel bedroom.
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
GPU-accelerated Whisper STT on NVIDIA Jetson Orin Nano using whisper.cpp with CUDA. OpenAI-compatible API.
A Custom Firmware Download Tool for DJI Drones Written in C#
Playing FM transmitter on various Microcontrollers without using any external hardware
MoshiRAG is a compact full-duplex speech language model augmented with asynchronous knowledge retrieval to improve factuality without sacrificing real-time interactivity.
Publishing Hy3 isolated Ollama + A100 deployment scripts and service generator.
peer-up just connects. Connect your devices directly - no accounts, no cloud, no subscriptions. Works even when your network blocks everything.
satindergrewal / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
This repository includes codes for comprehensive tutorials in Control / Robotics Engineering. The link of YouTube video tutorials are mentioned in description.
cut Claude Code token usage by rendering text context as images
Multi-tenant documentation publishing platform — turn one shared template catalog into many branded, zero-dependency static documentation sites.