Top Dev Tool Projects : Ghidra, AirLLM, xtool, Shaders, ts-rust & DigUp Transcript, AI Summary & Key Points

AI Engineering from Scratch is a free, open-source curriculum developed by rohitg00 for learning to build and ship AI systems end to end. Its 20-phase sequence covers development tooling, mathematical and machine-learning foundations, deep learning, NLP, computer vision, generative AI, LLM applications, agent engineering, Model Context Protocol (MCP), agent skills, reinforcement learning, and related topics, with implementations in Python, TypeScript, Rust, and Julia. The repository describes 511 lessons and approximately 329 hours of material; each lesson produces a reusable artifact such as a prompt, skill, agent, or MCP server. Learners are instructed to read the lesson documentation, type and run the code from the repository root, record command evidence and outputs, and make a small change before continuing. It provides routes for complete foundations, mathematics and machine learning, production LLM applications, agent engineering, MCP, agent skills, and Claude certification preparation. The repository is distributed under the MIT license and is accompanied by a website containing the same lesson content.

AirLLM is an open-source Python library for running large language model inference on GPUs with limited memory. It reduces GPU memory use by loading and processing one model layer at a time instead of holding the entire model in GPU memory; for sparse mixture-of-experts models, it streams individual experts as needed. The project is designed to run large models without requiring quantization, distillation, or pruning, and provides a pip-installable package with support for multiple model families, CPU inference, macOS, and optional model compression and quantization features.

Anatomy is an open-source agent skill for Claude Code, Antigravity, OpenCode, and Codex that explains technical ideas by constructing interactive isometric illustrations of physical machines, instruments, tools, or other mechanisms. It uses a workflow that collects the relevant numbers, invents a physical object for the concept, creates a parts list and geometry, renders parts back to front, adds interaction, and verifies the result with geometry and browser checks. The skill can produce standalone HTML pages, embedded SVG files, or React/Next.js components. Its SVG kit provides isometric solids, round parts, pipes, cables, four-tone shading, animation, cards, and live readouts; optional WebGL layers add effects such as fire, exhaust, water, caustics, light, and glow, while a beta 3D mode re-projects and re-shades moving parts each frame. The repository includes Node build scripts, complete examples, React components, reference guides, and headless Chrome tools for screenshots, scripted interaction, line-end checks, and geometry audits. It uses Node.js built-in modules without npm dependencies for the kit and examples, with React 18+ required for React output and Chrome or Chromium required for browser checks. The project is distributed under the MIT license. Its stated limits include not being a chart library, not targeting people or exact maps, and requiring WebGL for shader effects.

ascii is a TypeScript library for adding animated ASCII art to web pages. It provides pieces including scenes, interface elements, charts, text effects, language logos, distribution logos, shapes, physics simulations, nature scenes, and generative patterns, rendered as text in a <pre> element or as colored graphics on a canvas. It supports React, Next.js, Astro, plain HTML through the <ascii-art> custom element, and direct TypeScript usage with its mount API. Pieces can be bundled as modules or loaded by name; options control frame rate and piece-specific settings, while labels support screen readers and reduced-motion users see the first frame by default. The project also provides animated SVG versions of selected logos, companies, and distributions for use in GitHub READMEs. It is written by bas3line and distributed under the MIT license.

DeepSeek Bot (DS Bot) is an Apache-2.0-licensed plugin for DeepSeek Harness that turns its sessions into user-configured, long-lived bots. Each bot uses a selected DeepSeek Harness model and stores editable memory on the user's computer; a main bot can manage other bots and group chats, while bots can hand work to one another with @ mentions and return results asynchronously. Group-chat administrators route requests to other bots, and shared capabilities can provide MCP servers, skills, and packs, with approval required for local MCP commands. Usage can be viewed by time, bot, and model, and data remains in the DeepSeek Harness home directory. It is an independent community project, not an official DeepSeek product.

DigUp is a free, open-source macOS menu bar app for searching files by their contents, including images, PDFs, documents, audio, video, screenshots, and optionally source code. It runs on Apple Silicon Macs with macOS 14 or later and keeps indexed data on the device. DigUp uses Google DeepMind's multimodal EmbeddingGemma 2 through llama.cpp and Metal. It converts images, document passages, video frames, and overlapping audio segments into a shared vector space, then combines semantic nearest-vector search with exact-word matching. Results can open a video or recording at the relevant moment, a PDF at the matching page, or code at the relevant line in a configured editor. The app reads only selected folders, excludes sensitive and ignored file types, and does not upload indexed files. It downloads the model once and checks for updates, with telemetry and accounts not required. DigUp can be installed from a DMG or Homebrew, includes a command-line tool, and is licensed under the MIT License.

ESP32 iPhone Agent is an open-source AI automation tool that lets a vision model control a real iPhone without installing an app, using a computer, AirPlay mirroring, and an ESP32-S3 board acting as a USB mouse and keyboard. UxPlay receives the AirPlay stream, a GStreamer pipeline converts it into JPEG frames, and the computer sends relative pointer, typing, scrolling, and key commands to the board over Wi-Fi. A planner model creates a short plan from the task and current screen, while an actor model examines each subsequent screenshot and selects actions such as tapping, swiping, drawing, typing, pressing keys, going home, or finishing. The server tracks and recalibrates the relative pointer, checks whether the screen changed after each action, and can retry or re-plan after missed actions, repeated actions, dropped links, or invalid model responses. The project provides a Python/FastAPI server and browser-based interface with live phone control, logs, screenshots with action overlays, manual controls, calibration, and an emergency stop. It runs on macOS or Linux with an OpenAI-compatible vision model, either remote or local; the phone requires AssistiveTouch but no Mac, developer account, jailbreak, or installed app. The repository is licensed under MIT.

ManimGX is an open-source Python animation engine by Academa for producing mathematical and 3D videos through an API compatible with Manim Community Edition. Its Rust and wgpu renderer exports scenes to MP4, while the same system can run in a browser using Pyodide in a Web Worker and WebGPU. It supports 2D and 3D scenes, surfaces, meshes, moving cameras, text, equations, plots, LaTeX or Typst input, synchronized speech through self.say(), and an inspect command for storyboards and 2D layout checks intended to provide feedback to coding agents. It can be installed with pip on macOS, Linux, or Windows with Python 3.13+, or used from npm for browser playback. ManimGX's own code is MIT-licensed; native wheels include components with separate licensing terms, including GPL-licensed x264.

OpenFilm is an open-source AI video agent and editor that lets coding agents such as Codex and Claude Code create films as HTML-based web pages. A film is a folder containing a film.html whose sections define timeline tracks of web pages, video, images, and audio; each animated page renders a frame at time t through a frame(t) function using browser technologies such as CSS, SVG, Canvas, WebGL, Three.js, GSAP, or video. Its browser-based Studio lets users move, scale, rotate, restyle, trim, and cut elements and clips, while saving edits back to the film files so agents can preserve them. The CLI can open films, inspect frames or ranges with look, render MP4 and other outputs, and obtain media through configured external providers. The look command checks frames in shuffled orders and reports changes, page errors, missing fonts or media, and text clipped by the frame. The CLI, Studio, desktop app, and format are MIT-licensed; local use requires Node, FFmpeg, and Git, while the desktop app bundles FFmpeg and a headless browser.

REA is a local reverse-engineering tool for AI agents, distributed as a CLI and MCP server. It connects agents to analysis providers such as Hopper and Ghidra, and can inspect native binaries, macOS applications, JavaScript and Electron applications, .NET assemblies, websites, packages, and controlled runtime behavior. Its investigation workflow decompiles or maps a target, follows strings, symbols, calls, references, and control flow, records evidence and limitations, and uses the findings to help reconstruct features in another project without claiming to recover original source code or automatically clone an application. Analysis runs on the local host; REA configures agent integrations and can optionally install Hopper, while Ghidra and Java must be installed separately. The project is distributed under the MIT license.

Shaders is an open-source WebGPU component library and design platform from Shader Effects, Inc. It provides declarative effects for React, Vue, Svelte, Solid, JavaScript, and Framer, including gradients, noise, glass, metal, lighting, distortions, transitions, blurs, and cursor effects. Components render as GPU-blended layers that can be nested, masked, and composed without writing shader code. Its visual editor at shaders.com lets users arrange components on an infinite canvas, adjust their properties, connect them to cursor or timeline inputs, and export the resulting component tree. The accompanying CLI connects a project to a Shaders account, detects the framework, installs selected effects as component files, and can search, preview, and update them. Custom components can be defined with JavaScript objects and WGSL pixel code. The engine, components, framework bindings, and npm package are MIT-licensed; the hosted editor, presets, and other platform features have separate terms.

Shipyard is an open-source desktop app and toolset for running coding agents on remote development machines such as VPSs, cloud VMs, and desktops while controlling them from a laptop. It gives each repository worktree terminals, browser tabs, dev servers, services, hooks, and automations; agents run on the remote machines, so closing the app or losing the laptop connection does not stop them. Shipyard supports agents including Claude Code and Codex, with a kanban for agents needing attention, a review inbox, and orchestration actions such as prompting, waiting, checking, looping, and handing work off. Projects can be configured through .berth/config.json, shareable kits, or machine configuration, while automations can run from events, schedules, or GitHub activity. Its components include the berthd daemon on each development machine, the berth laptop CLI and background agent, a Tauri and React desktop app, and React plugins. The repository provides installation scripts and prebuilt desktop and daemon releases, SSH-based machine pairing, private development-server URLs, and integrations that report Claude Code, Codex, and Cursor state. It is distributed under the MIT license.

Skills is a command-line tool for the open agent skills ecosystem. It installs reusable instruction sets defined in SKILL.md files into supported coding agents such as OpenCode, Claude Code, Codex, Cursor, and others. The `npx skills` CLI resolves skills from GitHub, GitLab, other Git URLs, local paths, or direct file and archive URLs; lists available skills, selects individual skills, and installs them project-wide or globally by symlink or copy. It can also generate a prompt for a skill without installing it, launch a supported agent with that prompt, search for skills, update or remove installations, and create new SKILL.md templates. Skills use YAML frontmatter with a name and description, and the CLI discovers them in standard agent and repository skill directories. The project is licensed under the MIT License.

Skills for Real Engineers is an open-source collection of small, composable agent skills by Matt Pocock for disciplined software development with Claude Code, Codex, and other coding agents. The skills support requirements clarification, project-language setup, test-driven development, debugging, code review, specification, planning, triage, and codebase surveys. The collection includes skills such as `/grill-me` and `/grill-with-docs`, which question the user about a proposed change before implementation, and a setup skill that configures an issue tracker, ticket labels, and documentation storage for a repository. It can be installed as a managed Claude Code plugin or copied into a project as editable files through the `skills` installer; the skills are intended to work with any model and can be adapted by the user.

Talorys is a free, open-source personal AI assistant that runs in the user's own Cloudflare account. It provides chat with streaming responses, inspectable and editable memories, tasks, notes, projects, and one-time or recurring reminders and routines; it is designed for one user, with no signup or developer-operated account. A React frontend on Cloudflare Pages sends API requests through a Pages Function and service binding to a private Cloudflare Worker. The Worker hosts a TalorysAgent Durable Object with SQLite-backed conversations, memories, tasks, notes, projects, sessions, settings, and automations. Workers AI provides streaming chat and tool calling, while Durable Object alarms run scheduled reminders and routines. Relevant memories can be selected for each prompt, with optional semantic recall and memory history for superseded facts. The npm installer, `npx create-talorys@latest`, deploys the application and configures authentication, secrets, resource names, and the service binding. The project reports no telemetry, analytics, tracking, or advertising code; data remains in the user's Cloudflare account, although Cloudflare processes chat data for its services. It is licensed under the MIT License and is designed for Cloudflare's free plan, subject to Cloudflare quotas.

ts-rust, also distributed as tsc-rs, is an experimental Rust port of Microsoft's native TypeScript 7 compiler. It includes the compiler, type checker, language server, and API, following the upstream Go compiler's command-line behavior and algorithms. It can be installed from npm with `tsc-rs` and used with `npx tsc-rs -p tsconfig.json`; standalone binaries are provided for Linux x64 and macOS arm64, while Windows and Linux arm64 are not yet available. The port also includes Effect language-service diagnostics when enabled through the corresponding TypeScript plugin configuration. The project is an early release with documented compatibility issues involving some monorepos, project-build output, and long editor sessions, and is licensed under MIT.

xtool is a cross-platform Xcode replacement for building and deploying iOS applications from Swift Package Manager projects on Linux, Windows, WSL, and macOS. Its command-line interface creates projects, builds and runs apps, manages the Darwin Swift SDK and Apple Developer Services authentication, communicates with Apple Developer Services, and lists, installs, launches, or uninstalls apps on devices. It also provides the XKit SwiftPM library for accessing Apple Developer Services and iOS devices from another Swift application.