glm‑coding‑helper is a Tampermonkey userscript plus a local CPU/GPU OCR server that automates the frantic “rush” purchase of Zhipu GLM Coding Plan subscriptions. It enables early button clicks, cycles through plan options, solves Chinese point‑selection captchas locally (using YOLO + PP‑OCRv6), and offers configurable auto‑click, multi‑window, and safety settings. The project provides portable Windows builds and online installers for macOS/Linux, with a one‑click start script that sets up a Python environment and launches a FastAPI OCR service.

PyOpenCL is a Python library that provides full, Python‑friendly access to OpenCL GPUs and other parallel devices. It offers RAII‑style resource cleanup, automatic error‑to‑exception conversion, and fast C++ bindings, with cross‑platform binary wheels and an MIT license, making it a practical tool for custom GPU‑accelerated code in AI and scientific computing.

A web-based user interface and API for controlling FarmBot automated gardening devices, featuring real-time messaging and farm design management.

A high-performance MinHash library written in Rust with Python bindings for fast near-duplicate document detection and Jaccard similarity estimation.

A deterministic linter and textlint preset that flags common LLM writing patterns (AI-slop) to help writing agents produce more human-like prose.

A collection of NVIDIA-maintained utilities for PyTorch that streamline mixed precision and distributed training through optimized CUDA extensions.

A Python library that automates ChatGPT login and interaction by reverse-engineering the API to mimic a real user, eliminating the need for a browser.

A Python library and command-line utility for extracting summaries from HTML pages and plain texts using various summarization algorithms.

A collaborative workspace for AI agents and humans to work together in shared channels and documents, built on the OpenClaw ecosystem.

An unofficial npm package that bridges the Vercel AI SDK with Anthropic’s Claude Code models via the official Claude Agent SDK. It supports streaming, multi‑turn sessions, native structured outputs (Zod schemas), tool usage, image handling, and fine‑grained Agent SDK options. Multiple provider versions map to AI SDK v4‑v7, with the current stable line (4.x) requiring Node ≥ 22 and Zod ^4.1.8.

A persistent memory and task coordination layer for AI coding agents that enables shared context, hybrid search, and atomic task management across different sessions and MCP clients.

An agent communication SDK that provides a unified interface for AI agents to interact with humans across multiple channels like Slack, Discord, and Telegram using a single handler.

An LLM-powered research monitoring system that automatically collects, filters, and analyzes papers from ArXiv and other sources to generate personalized daily reports.

MCP Feedback Enhanced is a security‑hardened MCP server that adds a web‑based (and optional Tauri desktop) UI for human‑in‑the‑loop feedback during long AI tasks. It works locally, over SSH, and in WSL, tracks sessions, supports images, markdown, timers, and multilingual UI, and is maintained as a fork of the original interactive‑feedback‑mcp project.

A lightweight, high-performance WebAssembly runtime that provides a secure sandbox for running LLMs, microservices, and plug-ins across edge devices and servers.

A privacy-focused, open-source browser extension for translating web pages, text, and subtitles using modular backends or offline local translation.

A modern, responsive Django admin interface that integrates AI-powered tools for text translation, summarization, and image generation directly into the admin panel.

A collection of AI-powered command-line tools for coding workflows, including terminal chat, automated code editing, and context-aware refactoring.

A browser extension that converts web page content into clean Markdown, optimized for feeding into LLMs with built-in token counting and multi-tab support.

Open-source installers that connect Codex CLI and Claude Code to the NeuroAPI service, providing secure, encrypted storage of API keys on Windows and macOS.

An open-source, multi-provider terminal coding agent built in Rust that provides a high-performance AI pair programmer with editor integration via the Agent Client Protocol.

aicommit2 is a CLI that automatically creates Git/YADM/Jujutsu commit messages using a wide range of LLM providers, with features like multi‑provider streaming, diff compression, code review, hook integration, and LazyGit support.

A plugin for the Bob translation app that enables translation, polishing, and grammar correction using OpenAI, Gemini, and other compatible LLM APIs.

A single SQL query interface for AI agents to access multiple data sources, reducing tool-call complexity and improving accuracy and cost efficiency.

A JavaScript application framework that allows Web engineers to train, serve, and deploy machine learning models by bridging the Node.js runtime with the Python ML ecosystem.

Bitterbot is a local‑first AI agent that keeps a biologically‑inspired, persistent memory, runs autonomous “dream” cycles to consolidate knowledge, can execute tools (web browsing, code, WhatsApp), and optionally participates in a P2P skill marketplace for USDC. Install via Node ≥ 22, run the onboarding wizard, and interact through a browser UI at http://127.0.0.1:19001.

A self-hosted photo management app that uses object recognition and color analysis to automatically organize and filter photo collections.

A modern cross-platform client for Ollama that provides a graphical chat interface for interacting with local AI models via API.

A modern web interface for chatting with local LLMs through Ollama, featuring local chat history and Markdown support.

A personal 24/7 AI assistant that integrates Claude or Opencode with messaging platforms like WhatsApp and Telegram to provide tool access and persistent memory.

An MCP server that provides intelligent code indexing and AST-based analysis to help AI assistants navigate and understand complex codebases.

A cross-platform AI assistant app for Android, iOS, and macOS that enables real-time chat, multimodal analysis, and the instant creation of web applications using various LLM providers.

An automated experimentation framework for Codex that improves local code by iteratively testing small changes against a defined benchmark and correctness checks.

A Python library providing a standardized API and benchmark environments for developing and comparing multi-objective reinforcement learning algorithms.

A Go-based protocol conversion and model routing proxy that unifies various AI provider APIs (Anthropic, Gemini, OpenAI) under a single OpenAI Responses API interface.

A collection of samples for Azure Cognitive Service Text-to-Speech, enabling developers to integrate natural-sounding AI voices into their apps via the Speech SDK or REST API.

A streamlined deployment wrapper for ChatTTS that provides a WebUI and one-click Colab setup for advanced text-to-speech generation.

ZCF is a zero-config setup tool that provides one-click initialization for Claude Code and Codex, automating the configuration of workflows, APIs, and agent systems.

A high-performance trainable sparse attention implementation that combines Flash Attention's memory efficiency with sparse computation for handling extremely long sequences in Transformers.

An HTTP proxy written in Java 21 that provides a unified API for various chat completion and embedding models.

A checkpointing and persistence library for JAX models that enables efficient saving and restoring of model states, including support for asynchronous checkpointing.

vLLM‑Moet is a patched vLLM fork that adds 2‑bit expert quantisation, FP4 recovery, tiered GPU/host/NVMe expert storage, and speculative decoding to run massive MoE models (e.g., 753 B GLM‑5.2) on consumer‑grade RTX PRO 6000 or RTX 5090 GPUs. It ships Docker images, custom SM 120 kernels, and a set of configurable knobs for memory‑speed‑quality trade‑offs.

GPT‑NeoX is an open‑source, Megatron‑based library for training billion‑parameter language models on multi‑GPU clusters. It adds DeepSpeed‑style optimizations, supports many launchers (Slurm, MPI, etc.), works on NVIDIA and AMD GPUs, and includes modern features like flash attention, Mixture‑of‑Experts, and preference‑learning fine‑tuning. Ideal for research labs with large compute budgets; for inference‑only use, Hugging Face `transformers` is recommended.

mancode is a Node‑based CLI that adds a privacy‑first, cross‑session workflow layer on top of AI coding assistants (Claude, Cursor, Copilot, etc.). It provides lightweight `solo` mode and heavier `/man`‑style planning, review, and team‑collaboration modes, persisting task references, plans, and evidence in a hidden `.mancode/` folder. The tool sanitises sensitive data before it leaves the machine, enforces engineering standards, and works with multiple agents via platform adapters. Install with `npm i -g mancode`, run `mancode init` in a project, and invoke the new `/man*` commands inside your AI assistant.

hermes‑claude‑auth is a Python runtime patch that lets the hermes‑agent use a Claude Code subscription after Anthropic added OAuth validation. It installs a .pth shim that monkey‑patches the agent’s request builder, adds the required billing header, fixes prompt layout, and implements auto‑wait for subscription‑window rate limits. The installer works on Linux/macOS and Windows, provides uninstall scripts, and includes git‑hook + cron recovery to survive hermes updates.

A specialized AI Agent skill that provides traceable A-share market sector data, policy analysis, and company/ETF mapping to enable verifiable financial research.

XGo is a natural-language-style programming language that simplifies Go's syntax and integrates C/C++, Python, and JavaScript/TypeScript libraries into a unified ecosystem.

A macOS‑only Swift tool that records mic and system audio locally, then transcribes both tracks on‑device using a Core ML speech model, producing speaker‑tagged transcripts without sending any data to the cloud.