Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
MiniMax M2.1, a SOTA model for real-world dev & agents.
Whoosh is a fast, featureful full-text indexing and searching library implemented in pure Python.
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
Simple calendar widget for Obsidian.
Implement a reasoning LLM in PyTorch from scratch, step by step
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
A framework for building native applications using React
A JavaScript engine optimized for running React Native.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
React - The Complete Guide Course Resources (Code, Attachments, Slides)
MicroPython firmware for Pybricks-compatible devices.
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Post-training with Tinker
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Learn the building blocks of how to build DeepSeek from scratch.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows — particularly Claude Code
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
An extremely fast Python package and project manager, written in Rust.
Konva.js is an HTML5 Canvas JavaScript framework that extends the 2d context by enabling canvas interactivity for desktop and mobile applications.
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
A powerful AI coding agent. Built for the terminal.
A guidance language for controlling large language models.