Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

Monitors company career pages for new job postings and surfaces them in a single dashboard.

Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.

TrueNAS UI

A self hosted virtual browser that runs in docker and uses WebRTC.

Create your own playable 2D characters and maps, powered by fal.ai

Lightweight & fast OCR models for license plate text recognition.

WebUI for Garage Object Storage Service

Unified Agentic AI and Business Intelligence Platform

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Fully Open Language Models with Stellar Performance

Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming c…

Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

PyTorch Code for Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation

AI agent autonomously optimizing RAG retrieval pipelines against your own documents

Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no API key.

The most RAM efficient harness

Code & Train GPT-5 small version - for learning.

Train your own LLM from scratch

A minimal and efficient Pytorch implementation of OpenAI's GPT (Generative Pretrained Transformer).

Implementation of the GPT-3 paper: Language Models are Few-Shot Learners

An implementation of GPT-3 model described in the original paper

Modern LLM implementation

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".