A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

A straightforward method for training your LLM, from downloading data to generating text.

A ~9M parameter LLM that talks like a small fish.

OSINT & recon toolkit // 100+ tools, one-command installer, SOCMINT, GEOINT, network recon, dark web, forensics & more.

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

A vector index built on TurboQuant, written in Rust with Python bindings

Fully automatic censorship removal for language models

Use Claude Code, Codex, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (…

Repo to accompany my mastering LLM engineering course

A group of notebooks and other files which can help you learn AI from scratch.

Collection of all Files related to the anUNet and NOSA v3.3

A complete computer science study plan to become a software engineer.

Awesome LLM Books: Curated list of books on Large Language Models

🍃 Organic Maps is a free Android & iOS offline maps app for more than 6M travelers, tourists, hikers, and cyclists. It uses crowd-sourced OpenStreetMap data and is developed with love by the commun…

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Links to resources talking about how to learn & understand mathematics, and mathematical language, terminology and notation.

Agent skill to turn any arxiv paper into a working implementation

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

Learn LLM internals step by step - from tokenization to attention to inference optimization.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

real time face swap and one-click video deepfake with only a single image

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

Step-by-step guide of how I setup opencode's agentic workflow to be compatible with ollama's models that are capable of using tools

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.

A secure, open-source code interpreter API with sandboxed Docker execution. Compatible with LibreChat.