-
Third Intelligence
- https://ksterx.me/
- @kster_xyz
Stars
29 editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
Japanese Input Method System for Linux, macOS, Neural Kana-Kanji Conversion Engine
🦀 Clawd, a menu bar crab that shows your Claude Code sessions at a glance — walking while Claude works, bouncing when it needs you
OBLITERATE THE CHAINS THAT BIND YOU
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…
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori…
Official implementation of "Continuous Autoregressive Language Models"
A Model Context Protocol (MCP) server that provides structured spec-driven development workflow tools for AI-assisted software development, featuring a real-time web dashboard and VSCode extension …
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
textlintプリセット:AIっぽい記述パターンを検出し、より自然な日本語表現を促すルール集
A modern Python library for SLURM workload manager integration with workflow orchestration capabilities.
Scalable toolkit for efficient model reinforcement
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
A lightweight, powerful framework for multi-agent workflows
Mega-Gorilla / Discovery
Forked from MineDojo/VoyagerAn Open-Ended Embodied Agent with Large Language Models
The official Python SDK for Model Context Protocol servers and clients
A simple tool for generating random, memorable names - better than UUIDs
Train transformer language models with reinforcement learning.
🥰 Building AI-based conversational avatars lightning fast ⚡️💬
ChatdollKit enables you to make your 3D model into a chatbot