MDia is a Python library that formalises LLM intermediate reasoning as reusable “dialect cards” (LSFs) and provides a deterministic eight‑stage pipeline (collect → create → evolve → profile → select → run → validate‑rules → report) for generating, evolving, profiling, routing, and auditing these protocols across heterogeneous models. It supports black‑box LLM APIs, offers several routing plans, includes a 100‑rule bank, and guarantees reproducibility by freezing decisions before test evaluation. The repo includes a toy offline demo that runs without any API keys, extensive documentation, MIT licensing, and a citation to the ICML 2026 poster and arXiv paper.

A session log viewer for Claude Code that transforms raw local JSONL files into readable, interactive conversations across desktop, web, and TUI interfaces.

A unified CLI for managing local AI skills, browser automation via a Chrome extension, and terminal-based AI chat.

A voice input addon for Fcitx5 that enables local or cloud-based speech-to-text with LLM-powered post-processing and text modification.

An open-source, 100% local audio transcription and subtitling suite with a web UI that uses FasterWhisper for fast, private processing.

A collection of plugins and configuration settings for AI coding tools like Claude Code and Cursor to reduce over-engineering and eliminate AI-generated buzzwords.

ReqLLM is an Elixir library that unifies calls to dozens of LLM providers (OpenAI, Anthropic, Azure, Google Gemini, etc.) behind a single, high‑level API. It offers functions like `generate_text/3`, `stream_text/3`, and `generate_object/4` that work across 1,200+ models, handles streaming via Finch, validates structured outputs, tracks token usage and estimated cost, and provides built‑in Telemetry. Keys are managed automatically from env files or in‑memory storage, and the library includes extensive provider guides and a Discord community for support.

A standalone C++ inference engine for SAM-3D-Body that regresses 3D human body pose, shape, and camera parameters from 2D images without Python dependencies.

A desktop application for AI-powered face swapping and enhancement across images, videos, and live webcam feeds, featuring professional editing tools and GPU acceleration.

An engine-agnostic Java framework for deep learning that allows Java developers to build, train, and deploy models using a native Java experience.

A toolkit that integrates Databricks expertise and tools into AI-powered code editors, allowing developers to build Databricks pipelines, jobs, and apps using their preferred AI assistants.

A tool that centralizes AI coding assistant instructions into a single source of truth and automatically distributes them to various AI agent configuration files.

A Python framework for producing structured outputs and building agentic AI workflows using tasks, specialized agents, and type-safe results.

A tool that converts text corpora into interactive knowledge graphs of concepts using local LLMs, enabling advanced text analysis and Graph RAG.

AnySearch MCP Server is a real‑time, MCP‑compatible backend that provides general web search, vertical‑domain search, parallel batch search, and URL‑content extraction. It works with popular AI‑assistant IDEs (OpenCode, Claude Code, Cursor, VS Code, Windsurf, Cline) via simple JSON configuration, supports optional API‑key authentication for higher rate limits, and even allows anonymous use. The README details registration, key handling, client‑specific config snippets, and the four tool endpoints (`search`, `get_sub_domains`, `batch_search`, `extract`).

A library for fine-tuning LLMs, vision, audio, and OCR models natively on Apple Silicon using an Unsloth-compatible API for easy prototyping and scaling to cloud GPUs.

okf‑skills is a Claude Code plugin/skill set that lets agents create, validate, back‑fill and visualise Open Knowledge Format (OKF) bundles – markdown‑based knowledge packs with provenance, trust and staleness metadata. It ships as a Claude marketplace plugin, as skills.sh‑discoverable agent skills, a GitHub Action for CI validation, and a read‑only MCP server. Install via `/plugin install okf@scaccogatto` or `npx skills add scaccogatto/okf-skills`. Use the `/okf:*` commands to produce bundles, run the deterministic validator, or render an interactive HTML graph. The repo is MIT‑licensed and actively CI‑tested.

GigaBrain‑0.7 is an open‑source, large‑scale vision‑language‑action model for robots. It is pretrained on 37 k h of heterogeneous embodied data, supports eight robot embodiments, and ships with training scripts, benchmark suites (VLM‑Benchmark, RoboColiseum, RoboTwin 2.0, EBench), and ready‑to‑run inference servers that integrate with ROS.

Cookiecutter Data Science (CCDS) is a CLI tool that creates a standardized, best‑practice project skeleton for data‑science work, including folders for raw/processed data, notebooks, a Python package with training/prediction scripts, docs, and a Makefile. Install via pipx, run `ccds`, answer prompts, and you get a ready‑to‑use, reproducible project layout.

A multi-modal, autonomous AI persona framework that creates a proactive voice assistant with vision, long-term memory, and a low-latency response pipeline.

EventCatalog is an open‑source web‑based documentation platform for software architecture. It lets teams record domains, services, messages, and schemas, provides AI‑driven natural‑language search, searchable schema explorers, flow visualisation, versioning, and enterprise features like OAuth2 and RBAC. Install with a single `npx` command, then run locally at `http://localhost:3000`. The project ships as several npm packages (core UI, SDK, CLI scaffolder, visualiser).

A cross-platform, Rust-based terminal multiplexer engine that provides tmux-compatible commands and typed SDKs for programmatic terminal automation and orchestration.

A high-productivity Python framework for robotics research and education providing tools for kinematics, dynamics, planning, and simulation of manipulators and mobile robots.

A Python library for building scalable synthetic data pipelines, providing bulk inference and structured output tools to curate high-quality datasets for post-training.

Gorilla is a framework and set of models designed to enable LLMs to accurately invoke massive numbers of APIs and tools while reducing hallucinations.

A Python library and CLI tool that automates the discovery of Cloudflare Turnstile sitekeys and generates valid tokens via the Peak API to bypass security challenges.

OpenCatESP32 is the firmware that runs Petoi’s open‑source quadruped robots (Bittle X, Nybble Q, and the upcoming Quaddle) on an ESP32‑based BiBoard. It provides real‑time gait control, a motion‑recording “Puppet Mode”, and enough processing power to add vision or reinforcement‑learning experiments, all programmable via the Arduino IDE.

A tool-calling quality benchmark for LLMs that evaluates tool selection, parameter precision, and agentic workflow reliability across various self-hosted serving stacks.

An Agent Skill that converts Chinese classical poems into vertical, Chinese‑painting‑style animated videos (1080 × 1920) using AI image generation, a Gemini‑based image‑to‑video Docker container, brush‑stroke subtitles, and automated QA.

A Rust and Tauri-based MITM framework that intercepts Codex CLI API requests to bypass safety filters via system prompt injection and response tampering.

An autonomous multi-model AI agent swarm for offensive and defensive security automation, designed to solve CTFs and perform penetration testing by coordinating diverse LLMs via a shared blackboard.

WebRPA is an open‑source, Windows‑only visual RPA suite that lets users build web, desktop and Android automation flows by dragging‑and‑dropping from a library of 571 modules. It ships with bundled Python 3.13 and Node.js runtimes, runs completely offline, and includes an AI assistant that can generate, debug and self‑heal workflows via OpenAI‑compatible APIs. Features include visual debugging, versioning, one‑click EXE packaging, optional heavy‑weight capability packs, and a modern React + FastAPI stack. Licensed under AGPL‑3.0 for non‑commercial use, with a commercial license available.

A private, DIY home security camera system for Raspberry Pi that uses end-to-end encryption to avoid cloud surveillance.

A design automation tool for representing and compiling large-scale fault-tolerant quantum computations based on surface code and lattice surgery.

A high-performance, client-side toolkit for parsing, viewing, and editing IFC (BIM) files using a Rust-WASM core and WebGPU rendering.

An open-source MySQL branch that integrates DuckDB for high-performance analytics and native HNSW vector search for AI applications.

A secure, Rust-based Apache Iceberg REST Catalog that centralizes access control and table management across multiple compute engines.

itr‑wala is an open‑source CLI that prepares Indian individual tax returns locally. It uses an LLM only to read PDFs, while a thoroughly tested Python engine does all the statutory calculations. The tool validates inputs, compares old vs. new regimes, and outputs a ready‑to‑type filing pack; you still manually submit and pay on the government portal.

A collection of modular AI workflows (Codex Skills) for Xiaohongshu operations, helping creators systematically optimize their profiles, content planning, and conversion paths.

A comprehensive library of agent skills for AI assistants to help researchers draft, structure, and audit manuscripts specifically for Nature-series journals.

A native desktop companion for OpenAI Codex that provides a GUI for managing accounts, routing, sessions, and local configurations to avoid manual file editing.

A curated marketplace of plugins for Claude Code that provides specialized skills, writing guides, and MCP servers for enhanced productivity.

A Codex skill that identifies potential first customers for startups by analyzing public signals of pain and demand to create an evidence-backed prospect shortlist.

A Python library for differential inverse kinematics based on the MuJoCo physics engine, enabling robots to reach targets while avoiding collisions and respecting joint limits.

A specialized IDE replacement for orchestrating multiple AI agents in parallel, using ephemeral worktrees and linked task cards to automate complex coding workflows.

SplatTransform is an open‑source library and CLI for converting, editing, and analysing 3‑D Gaussian splat data. It supports many input/output formats (PLY, SOG, SPZ, GLB, HTML, voxel, WebP, etc.), offers geometric transforms, filtering, decimation, LOD streaming, collision‑mesh generation, and GPU‑accelerated operations. Install via npm (or use the Docker backend) and run commands like `splat-transform input.ply output.sog` or chain actions (`-s`, `-t`, `--filter-box`, `--decimate`). Ideal for researchers, engine developers, and content creators working with neural‑graphics splat representations.

A cross‑platform command‑line interface for Higgsfield’s suite of generative AI models (image, video, 3D, audio) plus utilities for building React web apps, publishing browser games, and managing personal “Soul” avatars—all from the terminal.

A command line tool and VS Code extension for versioning data and ML models, tracking experiments, and managing reproducible ML pipelines.