Stars
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
All your AI providers, machines, and agent harnesses in one place. Free & native
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!
d-Matrix DMX Compressor: A Pytorch toolkit for nn.Module transformations supporting advanced quantization, sparsity, and elementwise function approximations.
[EMNLP 2025] Dataset and Code of "PersonaGym: Evaluating Persona Agents and LLMs"
Livro de técnicas de Go, utilizando somente LaTeX, com diagramas vetoriais. (English: A book about Go techniques, using only LaTeX, with vector diagrams.)
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
CyberBoard Play by EMail system for Windows
MegaMek is a networked Java clone of BattleTech, a turn-based sci-fi boardgame for 2+ players. Fight using giant robots, tanks, and/or infantry on a hex-based map.
Language Server Protocol for accessing Large Language Models
PyTorch native quantization for training and inference
Package to allow making API calls to LLMs with context from emacs buffers.
Type-safe, ergonomic, polymorphic optics for TypeScript
LSP server leveraging LLMs for code completion (and more?)
Secure environments for developers and their agents
A blazingly fast LSP client for Emacs
(Curated) Repository of RetroArch and related ports for ReShade
GitHub Action That Submits Argo Workflows From GitHub
Auto-Dark-Emacs is an auto changer between 2 themes, dark/light, following MacOS, Linux or Windows Dark Mode settings
EAF, an extensible framework that revolutionizes the graphical capabilities of Emacs