Lists (1)
Starred repositories
A offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.
An AI co-scientist powered by Claude Scientific Skills running on your desktop.
A simple TUI for serving local LLM models. Pick a model, pick a backend, serve it
Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.
Open-source orchestration for zero-human companies
AI agents running research on single-GPU nanochat training automatically
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
Agent harness to make your slop code well-engineered and beautiful.
Open-source alternative to Higgsfield AI — Free AI image generation & cinema studio with 20+ models (Flux, SDXL, Midjourney, Ideogram). Self-hosted, customizable, MIT licensed.
SimpleMem: Efficient Lifelong Memory for LLM Agents
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.
A unified REST API that wraps web-based LLM sessions (ChatGPT, Claude, Google AI Studio) into a standard interface using headless automation. Access your web-tier subscriptions programmatically wi…
This repo contains implementation of 25+ prompt engineering techniques.
Fara-7B: An Efficient Agentic Model for Computer Use
Open-source AI hackers to find and fix your app’s vulnerabilities.
Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
HackGPT Enterprise is a production-ready, cloud-native AI-powered penetration testing platform designed for enterprise security teams. It combines advanced AI, machine learning, microservices archi…
From baby GPT to diffusion GPT: An annotated implementation of a character-level discrete diffusion model (adapted from Karpathy’s baby GPT).
Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"
[ICLR 2026] Official PyTorch Implementation of RLP: Reinforcement as a Pretraining Objective