Dynamic context pruning plugin for OpenCode - intelligently manages conversation context to optimize token usage

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

This project aims to enhance the working environment on Windows

Simple frontend for LLMs built in react-native.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Slimmed, cleaned and fine-tuned oh-my-opencode fork, consumes much less tokens

omo; the best agent harness - previously oh-my-opencode

Glamourous agentic coding for all 💘

An ultra-light MacOS utility that helps hide menu bar icons

Fork of: The open source coding agent.

A skill file for removing AI tells from prose

A syntax-highlighting pager for git, diff, grep, rg --json, and blame output

List of Permanent Free LLM API (API Keys)

Download your Spotify playlists and songs along with album art and metadata (from YouTube if a match is found).

Fast linters runner for Go

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

A collection of 130+ specialized Codex subagents covering a wide range of development use cases.

A Magisk Module to monitor and fix potential Bootloops and SystemUI failures.

AI agents running research on single-GPU nanochat training automatically

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

Claude Code skill that removes signs of AI-generated writing from text

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

The open source coding agent.

A terminal workspace with batteries included

top #1 and most feature rich GPT wrapper for git — generate commit messages with an LLM in 1 sec — works with Claude, GPT and every other provider, supports local Ollama models too

ZeroTier for magisk ✅ App controller ✅

Automated Tailscale updater for GL.iNet routers: periodically checks for new releases, downloads the correct build, and installs/updates Tailscale reliably via script (for OpenWrt/GL.iNet firmware)

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.