-
Link Digital
- Bitola, Macedonia
Starred repositories
A lightweight, lightning-fast, in-process vector database
Experimental heterogeneous DeepSeek inference across RTX PRO Blackwell and GB10 GPUs, with RDMA expert disaggregation.
Towards a More Autonomous Agent System
Hover over an element and press Shift to inspect its CSS styles
Fast & opinionated local AI routing: one MCP server that loads local image and video models on demand on your own GPU box (DGX Spark first)
A Python framework for modular, self-contained skill management for machines.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
DeepSeek-V4.1-Flash-1017 on two NVIDIA DGX Sparks (GB10) with TensorFold TP2: scripts, chat-template fix, speed and quality results
GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold
Your always-on AI coworkers that move between text, calls, and Slack.
Local typed decisions, contrastive data curation, and model evaluation.
A syntax-highlighting interface for git, diff, blame, and grep/ripgrep
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Skills for Real Engineers. Straight from my .agents directory.
π Token-Oriented Object Notation (TOON) β compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
Agent Skills for NVIDIA products β install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
A vector index built on TurboQuant, written in Rust with Python bindings
π©΅ A free, open-source app store for developers' releases on GitHub, Codeberg & Forgejo β browse, discover, and install apps with one click. Formerly GitHub Store.
0xSojalSec / airllm
Forked from lyogavin/airllmRuns 405B LLMs on 8GB VRAM
Skills for the Gemma and model/agent interactions
RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust.
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
A curated list of reranking models, libraries, and resources for building high-quality Retrieval-Augmented Generation (RAG) applications.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Build and run agents you can see, understand and trust.