MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.

Search the seas for your lost treasure.

AI on the command line

Send emails from your terminal 📬

Your CLI home video recorder 📼

🐈 A collection of LLM inference providers and models

Make SSH apps, just like that! 💫

Style definitions for nice terminal layouts 👄

A powerful little TUI framework 🏗

The glamourous AI coding agent for your favourite terminal 💘

Post-training with Tinker

Turn a tRPC router into a type-safe, fully-functional, documented CLI

Official Sentry SDKs for JavaScript

Developer-first error tracking and performance monitoring

Simple, powerful and flexible site generation framework with everything you love from Next.js.

The most comprehensive authentication framework for TypeScript

Public code packages indexed in Chroma

Terraform Provider for ClickHouse Cloud

Code review for AI native teams. Native Electron app for reviewing pull requests dramatically faster than Github web. Specialized for handling reviews for background agents working on multiple conc…

Contrib repository for the OpenTelemetry Collector

Emdash is an orchestration layer for running multiple coding agents in parallel in isolated Git worktrees

Managed Agent Posttraining

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

The AI Browser Automation Framework

Better Stack JavaScript client

The System Initiative software

OpenTelemetry transport for Pino

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and…

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)