Stars
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
The pretty much "official" DSPy framework for Typescript
A community-driven knowledge base of practical patterns for Effect-TS.
CLI tool that uses Cerebras's Qwen3 model to generate explanations of code in < 0.5s
A powerful AI coding agent. Built for the terminal.
Lightweight coding agent that runs in your terminal
The edge and AI gateway for agentic apps. Arch handles the messy low-level work in building agents like applying guardrails, routing prompts to the right agent, and unifying access to any LLM. It’s…
Bare metal to production ready in mins; your own fly server on your VPS.
A Neovim (lua) plugin for working with a markdown zettelkasten / wiki and mixing it with a journal, based on telescope.nvim
Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claud…
Go SDK for working with the Paddle API in server-side apps.
Firefox user.js for A078 speed, privacy, and security. Your favorite browser, but better.
Firefox privacy, security and anti-tracking: a comprehensive user.js template for configuration and hardening
a better dotenv–from the creator of `dotenv`
An open-source & self-hostable Heroku / Netlify / Vercel alternative.
A collection of learning resources for curious software engineers
lint, hover, goto, autocomplete, and twoslash extensions for CodeMirror + TypeScript
A Go / TypeScript meta-framework with first-class support for React, Solid, and Preact – built on Vite.
A terminal workspace with batteries included
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
🤞 The SolidJS component library you've hoped for.