Top Dev Tool Projects : LLVM, OpenCode, WebLLM, manim, Aspire & Sugar High Transcript, AI Summary & Key Points

Agent Skills is Google's repository of installable skills for Google products and technologies, including Google Cloud. The skills provide Markdown-based procedures for tasks such as onboarding and authenticating to Google Cloud, deploying and managing AI agents, working with GKE, databases, networking, security, monitoring, analytics, advertising APIs, Firebase, Android, Dart, Flutter, and Google Maps Platform. Skills can be selected and installed with `npx skills add google/skills`; the repository also bundles plugins and MCP servers for agent harnesses including Claude Code, Codex, and Antigravity CLI. The repository accepts bug reports and contributions, and its skills are distributed under the Apache 2.0 license.

Aspire is Microsoft's multi-language, code-first toolchain for building, running, and deploying distributed applications. It defines services, frontends, containers, databases, caches, and their connections in code, then uses the Aspire CLI to run the application locally and carry the same definition into deployment. Aspire provides OpenTelemetry-based observability, service discovery infrastructure, project templates, integrations, an AppHost SDK, a dashboard, and a Visual Studio Code extension. Its repository includes the Aspire CLI and supports application definitions in languages including C#, TypeScript, JavaScript, Python, Java, Go, and Rust. The repository code is licensed under the MIT license.

Code-Graph-RAG is an open-source retrieval-augmented generation system for querying, understanding, and editing multilingual codebases. Its Tree-sitter-based parser extracts functions, classes, methods, modules, and relationships, then stores them in Memgraph under a unified graph schema. An interactive CLI converts natural-language questions into Cypher queries, retrieves source code by name or intent, and supports AI-assisted editing and optimization. It provides AST-based surgical patches with diff previews, structural search and rewriting through ast-grep, dead-code discovery by traversing call and reference edges, and runtime-call overlays from test traces or production eBPF profiles. The project also supports MCP integration and publishes the `cgr` command-line tool to PyPI.

Codewhale is an open-source coding agent for the terminal, built in Rust and independently maintained. It reads repositories, edits files, runs commands, inspects results, and works toward user-defined goals. It connects to hosted providers or local models through Ollama, vLLM, or SGLang, supports switching providers and models during a session, and can run interactively in a terminal UI or non-interactively with the `exec` command. Its control mechanisms include read-only planning, Ask, Auto-Review, and Full Access approval modes; `/undo` reverts the last turn and `/restore` returns the workspace to an earlier snapshot. It also supports saved sessions, durable goals, reviewable workflows, agent coordination, MCP servers, skills, hooks, and configurable agent roles. The project runs on the user's machine with the access granted to it, with optional operating-system sandboxing where supported, and is distributed under the MIT license.

Distilly is an AI agent skill-generation tool by titanwings that turns messages, documents, interviews, and other supplied sources into source-grounded Person Profiles. It models observable experience, decision patterns, expression, and ways of working, rather than claiming to clone a person, and supports colleague, relationship, and celebrity profile families. Each generated profile is packaged as an installable Agent Skill for supported hosts. Its workflow includes family-specific source collection and analysis, a six-dimension research pipeline for celebrity profiles, incremental file analysis and merging, conversational corrections written to a correction layer, and automatic version archiving with rollback to earlier versions. Supported source types include Lark, DingTalk, Slack, public X posts, WeChat exports, PDFs, images, email, Markdown, and pasted text, with source-specific setup requirements. The project documents native local Skill discovery for Claude Code, Hermes, OpenClaw, Codex, DeepSeek Harness, Pi, Grok Build, and OpenCode. It is distributed from its GitHub repository under the MIT License and is described as a demo version.

ECC is an MIT-licensed open-source agent-harness performance system maintained by affaan-m. It packages reusable skills, specialized agents, project rules, commands, hooks, memory, and security tooling for Claude Code as its primary target, with supported or limited adapters for Codex, Cursor, OpenCode, Gemini, Zed, GitHub Copilot, and other coding harnesses. Its core workflow turns plan, test, implement, review, verify, remember, and improve into reusable agent workflows. Skills are loaded for tasks such as test-driven development, research, security review, end-to-end testing, documentation, and refactoring; agents isolate planning, implementation, and review; rules provide always-loaded project or language standards; and hooks run event-triggered checks and session automation outside the model context. The optional Memory Vault stores inspectable Markdown handoffs and session context, while AgentShield scans agent files, hooks, MCP configurations, permissions, prompts, and secrets for security risks. ECC can be installed from its repository or through the ecc@ecc Claude Code plugin and ecc-universal package. The repository also provides selective installers, native or project-local integrations for several harnesses, a desktop dashboard, and the optional ecc-agentshield security-auditing package. Feature parity varies by harness: GitHub Copilot receives instructions and reusable prompts but not ECC hooks or agent delegation, while Codex has a native marketplace plugin with a narrower hook model.

HyperFrames is an open-source framework for turning HTML, CSS, media, and seekable animations into deterministic MP4 videos. It can be used locally through a CLI, by AI coding agents through skills, or as a rendering core for hosted authoring workflows. Compositions are defined as HTML with data attributes for timing, tracks, media, and sub-compositions. The renderer seeks each frame in headless Chrome, uses animation adapters such as GSAP, CSS, Lottie, Three.js, Anime.js, or WAAPI, and encodes the result with FFmpeg; its toolchain includes preview, linting, inspection, local rendering, browser-based editing, reusable catalog components, and AWS Lambda rendering. The project requires Node.js 22 or newer and FFmpeg, does not require React or a build step, and is licensed under Apache 2.0. Its agent skills support workflows including product videos, explainers, pull-request videos, captions, motion graphics, slideshows, music-driven videos, and general compositions.

LLVM is a collection of modular, reusable compiler and toolchain technologies. Its core processes intermediate representations and converts them into object files, providing libraries and tools such as an assembler, disassembler, bitcode analyzer, and bitcode optimizer. The project also includes components such as the Clang frontend, which compiles C-family languages to LLVM bitcode, the libc++ standard library, and the LLD linker. In the cited context, scriptc passes statically lowered TypeScript through its typed intermediate representation to LLVM.

ManimGL is an open-source Python animation engine for creating precise programmatic animations, particularly explanatory mathematics videos. Scenes can contain shapes, equations, and transformations and can be rendered to video or displayed in an OpenGL window. This repository is the original Manim project created by the author of 3Blue1Brown; it is distinct from the later Manim Community Edition. The package is installed as `manimgl`, runs on Python 3.10 or higher, and uses FFmpeg and OpenGL, with LaTeX optional for LaTeX rendering.

OpenCode is an open-source AI coding agent developed by anomalyco. It is used as a terminal-based coding agent and external coding harness, with a beta desktop application also available. The CLI includes a full-access build agent for development work and a read-only plan agent for code analysis and exploration; the plan agent denies file edits by default and asks permission before running shell commands. OpenCode also provides a general subagent for complex searches and multistep tasks, and can be installed through its shell installer, package managers, or platform-specific desktop packages.

OpenShaders is an open-source platform and registry for discovering, creating, publishing, and using shader code in websites. It is being built around a collection of WebGL and WebGPU shaders, a live editor for creating and collaborating on shaders, and ready-to-use React components and JavaScript modules, including a shadcn registry for installing shaders from a terminal. The platform is hosted at openshaders.com and is released under the MIT license; its full experience is still under development, while users can claim usernames, generate shaders, explore existing work, and copy shader code.

Pascal Editor is an open-source, web-based 3D building editor for creating and sharing architectural projects. It supports architectural elements and objects such as walls, slabs, roofs, zones, doors, windows, and furniture, along with plugins and publishable viewers. The editor is built with React Three Fiber and WebGPU. Its Turborepo monorepo separates scene schemas and state, 3D rendering, editing tools, built-in node definitions, viewer and capture runtimes, shared UI, a standalone Next.js app, and an MCP server that exposes scene tools, resources, prompts, and local storage to MCP-compatible AI hosts. The project can run locally through the @pascal-app/cli package, which starts a persistent editor and authenticated MCP service, stores projects in a local database, and manages the standalone runtime. Reusable editor, viewer, node, core, and capture packages are also distributed through npm.

PI-Desktop is a local-first desktop workspace for AI coding agents, built with Electron, a Rust host core, and the pi Agent Harness. It lets users open local projects, connect cloud or local models through providers such as OpenAI-compatible APIs, manage projects and long-running sessions, and review file changes and command output. Its architecture separates the React renderer, Electron desktop orchestration, Rust-managed permissions, filesystem access, SQLite persistence and secrets, and a pi Agent sidecar responsible for the agent loop, model interaction, and streaming. Agent, Plan, and Goal modes provide different approval boundaries; agents can read and edit files, run commands, and delegate exploration, implementation, research, testing, or review to background Subagents. The workspace supports MCP servers, Skills, installable Plugins, model and provider switching, session imports, notifications, context checkpoints, and a plugin marketplace. Conversations are stored locally as JSONL with a SQLite index, settings and logs remain on the machine, credentials use the operating-system keychain, and model requests go directly to the configured provider or endpoint. Plugin processes are permission-gated and isolated from the renderer, but plugins remain user-trusted code rather than a complete operating-system sandbox. It is an early-preview cross-platform application distributed for macOS, Windows, and Linux under the GNU Lesser General Public License v3.0.

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.

Sugar High is a lightweight, zero-dependency JavaScript syntax-highlighting library that runs in browsers and JavaScript runtimes and converts source code to HTML without requiring a DOM. It supports JavaScript, TypeScript, CSS, Python, C, Go, Java, Rust, JSON, Markdown, SQL, HTML, YAML, and other built-in languages and formats, with alias normalization for inputs such as filename extensions and Markdown fences. The library exposes a one-step highlight function and a composable core that separates syntax parsing from HTML rendering. Token classes can be customized with class maps or token hooks, while line-level hooks support highlighting or modifying generated lines; CSS custom properties provide theming. Its React package supplies Code and textarea-overlay Editor components, and its Remark plugin highlights fenced code blocks during Markdown processing. Sugar High also provides an opt-in experimental WebGPU entry for asynchronous, language-agnostic highlighting through gpu-lexer. It is distributed as npm packages under the MIT license, with a separate core entry for selective language configurations.

TeamAI is an open-source CLI for managing a team's skills, rules, documentation, agents, hooks, MCP configuration, environment settings, and knowledge across AI coding tools such as Claude Code, Codex, Cursor, CodeBuddy, WorkBuddy, and OpenCode. It is installed with npm as `teamai-cli` and uses a shared Git repository as the team's source of truth. The CLI distributes resources through an administrative `push` → review and merge → `pull` workflow. Session-start hooks can run `teamai pull` to synchronize the shared harness into project- or user-scoped local AI-tool directories; roles, tags, and subscribed source repositories control which resources members receive. TeamAI also provides a knowledge layer: `teamai import` and `teamai codebase` build a searchable team knowledge base and codebase graph, while `teamai recall` uses BM25 search with graph-boosted reranking and can deploy a recall subagent into supported AI tools. Code relationships are extracted with a WebAssembly tree-sitter parser for TypeScript/JavaScript, Python, and Go, with regex-based heuristic extraction as a fallback and for other languages. Additional commands support friction-based learning suggestions, privacy-scrubbed session summaries, maintenance of stale or low-confidence knowledge, usage digests, a web dashboard, member and role management, package and plugin installation, diagnostics, and uninstallation. The repository is maintained by Tencent and contributors and is licensed under MIT.

text-to-cad is a library of agent skills for creating, inspecting, sourcing, slicing, previewing, and handing off CAD, CAE, CAM, robotics, and hardware-design artifacts from local project files. Its skills generate and edit CAD models from plain-language or image requests, primarily producing STEP files with optional STL, 3MF, and GLB exports; preview local CAD and robot files in a browser; source off-the-shelf STEP parts; and create DXF drawings from Python sources or CAD geometry. Additional skills write URDF robot structures, SRDF/MoveIt2 planning and collision data, and SDF simulator models and worlds; check DXF and STEP files for SendCutSend; measure mesh printability by wall thickness, overhangs, support volume, and build orientation; slice supported meshes into validated, printer-profiled FDM G-code using slicer command-line tools; and dry-run, upload, and cautiously start local Bambu Lab print jobs. An experimental implicit-CAD skill creates browser-native models with GLSL signed-distance fields and CAD Viewer raymarch rendering. The library is installed with the Skills CLI, including `npx skills add earthtojake/text-to-cad`, or through provider-native plugins for Codex, Claude Code, and Grok Build.

WebLLM is an in-browser large language model inference engine developed by the MLC community. It runs model inference directly in web browsers using WebGPU hardware acceleration, without server-side processing, and can be used as an npm, Yarn, or CDN package for building web applications. Its MLCEngine exposes an OpenAI-compatible chat-completions interface with streaming, JSON-mode structured generation, seeding, and preliminary function-calling support. It supports model families including Llama, Phi, Gemma, Mistral, and Qwen, and can load custom MLC-format models consisting of model artifacts and WebAssembly model libraries. WebLLM provides Web Worker and Service Worker integrations, Chrome-extension examples, browser caching through Cache API, IndexedDB, or OPFS, and optional Subresource Integrity verification for downloaded model artifacts.

zane-ops is a self-hosted, open-source deployment platform positioned as an alternative to Heroku or Railway. It deploys applications, databases, and other services on personal servers using Docker Swarm and Caddy, and provides a dashboard for project management and log viewing.

ZaneOps is a self-hosted, open-source platform-as-a-service for deploying and managing static sites, web applications, databases, services, workers, and other workloads on a user's own servers. It uses Docker Swarm for scalability and Caddy for traffic handling, and provides a dashboard with project management, HTTP logs, and runtime logs. ZaneOps is positioned as a free alternative to platforms such as Heroku, Railway, and Render, and can be installed with a shell script.