Top Dev Tool Projects : MarkItDown, coder, YuE, Spotifast, colibri & Worktrunk Transcript, AI Summary & Key Points

Chrome DevTools for agents (chrome-devtools-mcp) is an MCP server from the Chrome DevTools project that lets coding agents control and inspect a live Google Chrome or Chrome for Testing browser. It uses Puppeteer for browser automation, including navigation and actions that wait for results, and exposes DevTools capabilities for recording and inspecting performance traces and insights, analyzing network requests, taking screenshots, and inspecting browser console messages with source-mapped stack traces. A CLI is also provided for use without MCP, with configuration options including headless, isolated, slim, concurrent-session, persistent-profile, WebSocket, and Android-debugging modes. It requires Node.js LTS, a current stable Chrome version or newer, and npm. Browser contents are exposed to MCP clients; performance tools may query the Google CrUX API, and usage statistics and update checks are enabled by default with an opt-out flag.

Coder is a self-hosted platform for cloud development environments and AI coding agents. It defines workspaces with Terraform and can provision them on EC2 virtual machines, Kubernetes pods, Docker containers, and other infrastructure, connecting users through a secure WireGuard tunnel and automatically shutting down idle resources. Coder Agents runs a native AI coding-agent loop in the control plane on the operator's infrastructure. It supports models from Anthropic, OpenAI, Google, Amazon Bedrock, and self-hosted providers without placing LLM credentials in workspaces, while providing centralized model governance, cost tracking, identity on actions, and audit logging. Workspaces can be accessed through existing IDEs including VS Code and JetBrains products.

Colibrì is a pure-C inference engine and open research platform for running large mixture-of-experts models on consumer and heterogeneous hardware without engine dependencies. It treats VRAM, system RAM, and storage as a unified multitier inference hierarchy, streaming expert weights from disk and coordinating placement, storage I/O, scheduling, kernels, speculation, and CPU/GPU overlap. The project provides chat, server, and web front ends, with support for CPU, CUDA, Metal, and dual-SSD streaming; its design rules prohibit silently changing model precision or router semantics when fast memory is insufficient.

DeepSelect is a high-performance CUDA and PyTorch implementation of TopK kernels for DeepSeek Sparse Attention and sampling workloads. It replaces vanilla `torch.topk` for supported inputs, covering bfloat16 lightning-indexer workloads and float32 sampling workloads, with configurable sorting, index type, value output, variable-length rows, and NaN handling. The repository reports 2–20× speedups against `torch.topk` on its benchmarks. It is distributed as an installable Python package from the `deepseek-ai` GitHub repository. Supported TopK values are limited to 4096 or less, and input tensors must meet specified stride and contiguity requirements; the optimized sampling case targets vocabularies of approximately 128K.

Hermes Agent is a self-improving AI agent developed by Nous Research. It provides a CLI and terminal interface, messaging gateway, and desktop interface for interacting with language models, operating terminals and browsers, and maintaining continuity across sessions. It supports model providers including Nous Portal, OpenRouter, OpenAI, and custom endpoints, along with terminal backends including local execution, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Its learning loop creates and improves skills from task experience, stores persistent memories, searches previous sessions with FTS5 and LLM summarization, and builds user profiles through Honcho. It can delegate parallel work to isolated subagents, run Python tool-calling scripts through RPC, schedule unattended jobs with a natural-language cron scheduler, and deliver results through Telegram, Discord, Slack, WhatsApp, Signal, email, and the CLI. The terminal interface includes multiline editing, slash-command completion, conversation history, interrupt-and-redirect controls, and streaming tool output. It also supports voice-memo transcription and cross-platform conversation continuity.

llmfit is a terminal tool that evaluates which local language models fit and run well on a user's hardware. It detects system specifications including RAM, CPU, GPU, and multi-GPU configurations, then scores models across fit, estimated speed, quality, and context dimensions while accounting for quantization and mixture-of-experts architectures. It provides an interactive terminal UI and a classic CLI, supports local runtime providers including Ollama, llama.cpp, MLX, Docker Model Runner, and LM Studio, and can output recommendations as JSON. Its benchmarking workflow can measure real token-per-second performance on a machine and contribute those results to the project's fit data.

MarkItDown is a Microsoft Python utility and command-line tool that converts files and office documents into Markdown for use with large language models and text-analysis pipelines. It aims to preserve document structure such as headings, lists, tables, links, and other content rather than produce high-fidelity human-facing document conversions. Its built-in converters handle formats including PDF, PowerPoint, Word, Excel, images, audio, HTML, CSV, JSON, XML, ZIP files, YouTube URLs, and EPUBs. It can be used through a Python API, command line, Docker, or third-party plugins; optional integrations support OCR with an LLM vision client, Azure Document Intelligence, and Azure Content Understanding, including multimodal conversion and YAML front-matter field extraction. The repository notes that conversion performs I/O with the current process's privileges, so untrusted inputs must be sanitized and the narrowest conversion method should be used.

oh-my-hermes (OMH) is a plugin and operating layer for Hermes Agent that adds model routing, coding workflows, specialist skills, project memory, and evidence-gated execution without replacing Hermes as the natural-language interface. It scores requests, selects workflows and model-and-effort categories, applies model-family-specific prompting, and can split accepted plans into parallel worktree-based lanes with typed results and verification gates. Its workflows cover interviewing, research, planning, coding delegation, quality assurance, performance work, and iterative plan-build-review loops; the terminal interface exposes phase-based todos, delegated-lane status, cost and token telemetry, and execution states that distinguish preparation, reported completion, and verified results. OMH also provides a file-backed, reviewer-gated memory store with provenance, review dates, conflict handling, and task-scoped recall packs, while leaving Hermes's native memory untouched. It is distributed as a command-line package and plugin with installation paths including a shell installer, Homebrew, Bun, npm, and Hermes skill tap.

Open Code Review is an open-source, AI-powered command-line code-review tool developed from Alibaba Group’s internal review assistant. It reads Git diffs and sends changed files to a configurable LLM through an agent with tool-use capabilities; the agent can read complete files, search the repository, and inspect other changed files for context before producing structured comments tied to source lines. Its hybrid architecture combines deterministic engineering with dynamic agent decisions: deterministic stages select and bundle files, match rules to file characteristics, and apply independent comment-positioning and reflection modules, while scenario-specific prompts and tools guide context retrieval and review. The `ocr scan` command audits complete files or directories without requiring a meaningful diff, and the project provides multilingual rules for issues including null-pointer exceptions, thread safety, cross-site scripting, and SQL injection. It supports configurable model endpoints, including OpenAI- and Anthropic-compatible endpoints, and requires Git 2.41 or newer.

OpenMAIC (Open Multi-Agent Interactive Classroom) is an open-source AI learning platform from THU-MAIC that turns topics or uploaded documents into interactive classrooms. It generates slides, quizzes, HTML simulations, and project-based learning activities, with AI teachers and classmates that can speak, draw on a whiteboard, conduct discussions, and respond to learners in real time. Its classic generation pipeline has two stages: an AI-generated lesson outline followed by scene generation for each outline item. The platform also provides a database-backed agent workbench that plans, builds, and revises courses through validated tools, with resumable sessions, follow-up steering, uploaded or web-retrieved materials, reusable skills, and support for importing PPTX files. Multi-agent orchestration uses a LangGraph director graph, while the playback and action engines handle classroom state and actions such as speech, whiteboard drawing, spotlights, and laser effects. OpenMAIC supports browser-only storage by default and can use PostgreSQL or S3-backed storage through its swappable storage packages. It accepts document, image, audio, and video materials through configured extraction providers, supports multiple LLM, media, speech, search, and local-provider configurations, and exports editable PPTX slides, interactive HTML, or classroom ZIP files. The repository is licensed under the MIT License, with separate terms for bundled components including an LGPL-licensed MathML-to-Office-Math package.

PR Lens is a pull-request visualization tool by Coldtea that generates animated architecture and data-flow diagrams and posts them inside GitHub pull requests. It maps a change's components and call paths, uses green for new elements, amber for changed elements, and red for removed elements, and provides step-by-step walkthroughs, nested diagrams, and interactive canvases with pan, zoom, and light or dark themes. It is available as a GitHub App, GitHub Action, CLI, or coding-agent skill. The CLI analyzes a diff against a merge base, produces a graph document, renders theme-paired SVGs, validates documents against a schema, and can compose the pull-request comment. The GitHub Action can use Gemini, OpenAI, or an OpenAI-compatible endpoint; the agent skill lets a coding agent generate and attach the diagrams. Repository configuration in .github/pr-lens.yml supports renames, exclusions, lane pins, and groupings. The repository documents Node 20.11+ and pnpm 10 requirements and is licensed under the MIT License.

RuView is an open-source Wi-Fi sensing platform from ruvnet that uses Channel State Information (CSI) captured by low-cost ESP32 sensors to turn disturbances in radio waves into spatial data. It detects presence and occupancy through walls, estimates breathing and heart rate without contact, recognizes activities such as walking, sitting, gestures, and falls, and uses RF fingerprinting to identify rooms and environmental changes. The platform also supports camera-free pose estimation, CSI recording and model training, and loading RVF and LoRA profiles. RuView can publish sensing data to Home Assistant through MQTT and integrate with Apple Home, Google Home, Amazon Alexa, and SmartThings through supported bridges and Matter. Its repository also documents local automation, room-level semantic states, and the RuView MetaHarness, an AI-assisted workflow for onboarding, calibration, training, verification, and checking sensing claims.

Spotifast is a native Spotify desktop client written in Rust with egui for Linux, macOS, and Windows. It uses librespot for local playback and Spotify Connect, without bundling a browser engine, and provides access to playlists, Liked Songs, saved albums, followed artists, podcasts, episodes, search, lyrics, playlist editing, Spotify links, and queue controls. Playback supports gapless audio, up to 320 kbps, optional volume normalization, an on-disk audio cache, device transfer and control, and network discovery of compatible Spotify Connect receivers. The application also includes a Winamp mini player with classic skins, a ten-band equalizer, projectM MilkDrop visualizations, system-tray operation, keyboard shortcuts, and platform integration such as MPRIS on Linux and command-line controls. Spotifast typically uses 100–250 MB of RAM according to its README and starts in under a second. Playback on the computer requires Spotify Premium; free accounts can browse and search but cannot play music through the app. It is distributed through packages and downloads including AUR, Homebrew, Flatpak, and source builds, and is licensed under the MIT License.

System Prompts Leaks is an open reference archive of extracted AI system prompts, stored as Markdown files and organized by vendor. It collects prompts captured from chat assistants and coding agents—including Anthropic Claude, OpenAI ChatGPT and Codex, Google Gemini, xAI Grok, Cursor, Copilot, VS Code, and Perplexity—as well as officially published prompts for comparison. The repository is updated regularly and is intended for developers and researchers studying the hidden instructions and rules supplied to AI systems before user messages.

vphone-cli is an open-source macOS command-line tool for creating and running virtual iPhones with Apple's Virtualization.framework and PCC research VM infrastructure. It targets Apple Silicon Macs running macOS 15 or later and automates the VM workflow from IPSW download and patching through DFU restore, custom firmware installation, and first boot. The tool supports multiple firmware patch variants, VM creation and management, SSH and VNC connections, IPA installation, and export/import or APFS cloning of VM bundles. Its host control socket provides programmatic screenshots, touch and swipe input, hardware-key events, and clipboard operations, with each action returning an inline screenshot; the repository also describes an MCP server named vphone-mcp for AI-driven end-to-end testing. Operation requires Xcode and the iOS SDK, several Homebrew dependencies, and macOS SIP/AMFI relaxation to permit the required private virtualization entitlements.

Whiteboard Animator is a CPU-only Python package and command-line tool that converts a finished whiteboard-style image into a hand-drawn reveal video. It can write detected text word by word, trace outlines, fill shapes with brush strokes, and decompose branched line art into sequential pen paths; narration audio can pace the drawing, and multiple scenes can be concatenated into one MP4. It is the render engine behind the Whiteboard format at Kinoslide. The engine identifies connected non-white pixel components and uses a bundled CRAFT text detector to distinguish text from drawn shapes. It orders components using relationships such as containers before contents, shapes before labels, reading order for text, and attachment of small dots to glyphs. It assigns reveal times based on component area or a region plan, then follows skeletons and outlines with reveal fronts, brush strokes, or sequential paths before streaming frames to FFmpeg. Rendering requires no GPU, API key, training, or model beyond the bundled text detector; an optional Gemini-based region-detection feature requires a Gemini extra and GOOGLE_API_KEY. The package provides the `whiteboard-animate` CLI and a Python API, requires Python 3.10 or later plus FFmpeg and ffprobe, and is distributed under the MIT license. It is intended for clean marker-style drawings on white backgrounds rather than photos, gradients, or textured backgrounds.

Worktrunk is a command-line interface for managing Git worktrees, designed for running AI coding agents in parallel. It addresses worktrees by branch name and computes their paths from a configurable template; its core commands switch to, list, merge, and remove worktrees, with an option to launch a command such as Claude Code after switching. It also provides hooks for local workflow automation, LLM-generated commit messages, merge and cleanup workflows, an interactive worktree picker with diff and log previews, shared build caches, CI status and AI-generated branch summaries, pull-request checkout, per-worktree development-server ports, and aliases with branch-scoped variables. It can be installed through Homebrew, Cargo, Winget, Arch Linux, Conda, or Pixi, and shell integration enables commands to change directories.

YuE2 is an open music-generation model and Python pipeline that turns lyrics and a style prompt into a symbolic melody-and-chord plan and then renders that plan as a complete stereo song with vocals and accompaniment. It supports zero-shot covers by using a transcribed melody score, and composition editing by allowing the score, lyrics, style, harmony, melody, tempo, or form to be revised before rendering. Its AR–NAR Mixture-of-Transformers backbone predicts symbolic scores and semantic tokens, generates acoustic latents with flow matching, and uses a VAE to decode them into 48 kHz audio. The staged API exposes plan(), generate_semantic(), synthesize(), and decode() operations; the repository also provides an agent skill for song generation, transcription, cover creation, ABC-score editing, and listening comparisons. The repository provides the YuE2-3B model and requires Linux, Python 3.12, and an NVIDIA GPU with BF16 support and 24 GB of VRAM for the documented quick start. First-party code, documentation, and the agent skill use Apache 2.0, while the model weights use CC BY-NC 4.0. The original YuE implementation is preserved on the repository's YuE-v1 branch.