An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Build your own AI SRE agents. The open source toolkit for the AI era ✨

KernelUNO - a light-weight unix-like shell for arduino UNO R3

This is my first project

Turn Videos into
ASCII Frames - real ascii frames (character-based frames that run smoothly in sequence)

Lambda is a minimal, function-driven coding agent designed to generate, debug, and optimize code efficiently.

Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero dependencies.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

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

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

TurboQuant WASM SIMD vector compression — 3 bits/dim with fast dot product. Requires relaxed SIMD (Chrome 114+, Firefox 128+, Safari 18+, Node 20+)

GNU Octave Mirror (https://www.octave.org/hg/octave). Report bugs and submit pull requests (patches) at https://bugs.octave.org

The hiring challenge for AI-native marketers. Beat Claude to get an interview.

Extracted system prompts from ChatGPT (GPT-5.5 Thinking), Claude (Opus 4.7, Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, Gemini CLI), Grok (4.3 beta), Perplexity, and more. Updated…

Hosts MLSys Competition Track Problems

The python library for easy aptamer design.

Research Component of DREAMS main module

Production ready toolkit to run AI locally

A cosy home for your LLMs.

A curated collection of high-quality interview questions and answers for AI-related roles. This repository helps candidates understand how interviews differ across roles, not just memorize answers.

This repository contains the Hugging Face Agents Course.

Inference at the speed of light.

A minimal AI summarizer. Uses Gemma-3 270M

Optimized Whisper models for streaming and on-device use

AirLLM 70B inference with single 4GB GPU

Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.

faceghost - is an ultra fast optimized video face anonymization engine 6.67x faster than deface

⚡ A Fast, Extensible Progress Bar for Python and CLI