Developer tools

Install a ready-made routine so your AI coding agent plans before it builds, tests its changes and reviews its own work from a fresh context.

Stroq scans your recent Claude Code and Codex sessions for keys that left your machine.

GitDiagram reads a public GitHub repository, or a private one with your token, and draws an interactive architecture diagram with each piece linking to its code.

Ask an AI agent to explore your codebase, plan changes and write code from your terminal or a desktop app.

Add ready-made instruction folders so Claude handles tasks like PDFs, slides and brand-styled documents the same way each time.

Find Go frameworks, libraries and software by topic in Awesome Go, a curated list for Go programmers.

Make your AI coding assistant reply with the next action first, numbered steps and no padding.

Describe the diagram you want in ordinary words, and your AI agent creates a file you can open in a browser.

Install ready-made skills so Claude Code, Cursor or Codex can make short videos, web pages and articles.

Put websites, apps and databases online using servers you control, for developers who want a Heroku- or Vercel-style dashboard on their own hardware.

Pull text, links and data from web pages or whole sites into files.

codebase-memory-mcp is an MCP server (a tool that plugs into AI coding assistants) that reads a codebase and builds a searchable knowledge graph of its functions, classes, call chains and cross-file links, so an agent can answer structural questions about the code in under a millisecond instead of reading files one at a time.

Ponytail is a plug-in skill that teaches AI coding assistants to write less code: the agent learns to prefer the shortest change that works — the project frames it as thinking "like the laziest senior dev in the room." The creator measured it on real Claude Code sessions across twelve feature tasks and reports about 54% less code on average (up to 94% where the agent would otherwise over-build, as with a date picker), roughly 20% lower cost and 27% faster runs, with every safety guard kept.

Turn Claude Code into an organized game team that plans, designs, codes and reviews your game with you.

Set up a service that creates and manages separate Kubernetes clusters on your own NVIDIA GPU servers.

Ask your coding agent for a part in plain words and get a STEP, STL, 3MF or GLB 3D model plus drawings.

Send requests to hosted, your-own-key, or local AI models through one gateway.

Get text answers from the huge Kimi K3 AI model using one CPU and no graphics card.

Send sign-ups, logins, orders and payouts and get an approve, step up, review or block decision with reasons.

Run big open-weight AI models on your own gaming PC and chat with them.

Let a coding agent draw a big arrow with a sign over any Mac window to show you which button to click.

Review code, test in a real browser and ship code changes with typed commands in your coding agent.

Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.

Type a task in plain English and watch an AI agent tap through apps on a real Android phone or emulator.

An add-on for AI coding assistants that maps code, docs, PDFs and images into a graph you can ask questions about instead of searching files.

Compress logs, tool output and files before they reach the AI model, so each request uses fewer tokens.

Point it at your AI agent and get a graded report of risky behavior, like misusing tools or leaking data.

Upload documents and ask questions with traceable citations.

Have an AI agent review screens, fix accessibility, refine type and colors, and build pages from designs.

Let an AI coding agent work on separate git branches inside an IDE, then review its changes and open a pull request.

Add ready-made science skills so your AI agent can run genomics, chemistry or data analysis tasks properly.

Train your own small chatbot from scratch on a GPU server, then chat with it in the terminal.

Apply image filters, warps, augmentations and feature matching as differentiable PyTorch operations.

Let an AI agent fetch web pages as Markdown, search the web and automate browser tasks without installing Chrome.

Open web pages without a screen, turn them into markdown or data, and drive them from scripts or an AI agent.

Continue your DeepSeek Harness sessions from a phone, another computer or a browser while the work keeps running on your own machine.

Claude How To teaches Claude Code with visual tutorials and copy-paste templates, for developers who have installed it and want working setups.

Load a big open language model from Hugging Face and generate text on a GPU with only a few GB of memory.

Hand tasks to an AI agent that runs on your own computer and uses your files and apps; for people who want one agent across Claude Code and Codex.

A command-line tool for Git worktrees, aimed at people running several AI coding agents at once.

Build React app interfaces with 150+ ready-made components and themes.

Have tests, scripts or an AI agent open web pages, click, type and check results in Chromium, Firefox and WebKit.

REA lets an AI assistant investigate an app, website, or program file and report what it finds with evidence.

Have your coding assistant build or audit web pages that avoid the usual AI look.

Help AI agents answer questions about company databases using reviewed definitions and SQL, with each answer showing its steps.

SkillSpector scans AI agent skills for vulnerabilities and malicious patterns, for developers who want to know whether a skill is safe before installing it.

Ollama lets you choose an AI model and chat with it on your own computer.

Make Claude design screens and components that follow design rules and pass accessibility checks.

New API gives developers and teams one place to connect model providers, route requests, control access, and track costs.

Compare hosted services with free tiers, from web hosting to email.

Connect your CLI coding accounts to one local proxy and use them from any OpenAI, Gemini or Claude compatible client or SDK.

Add a layer to Claude Code or Codex that splits tasks across teams of specialized agents and remembers past work.

Feed in past open, high, low and close prices and get a forecast of the next candles.

Treg is a marketplace and proxy for AI-agent tools such as SEO data, company lookups, scraping and image generation, with over 3,000 endpoints across 60-plus providers.

Send AI requests to one local server that routes across many providers' free tiers, for developers and coding-agent users who want to stack free quotas.

Have a team of AI agents research a stock and debate a trading decision.

Let an AI model reply with live charts, forms and tables instead of plain text.

Turn ideas, plans or repositories into interactive visuals with this assistant skill, for people explaining systems or organizing what they want to learn.

Test running apps for security flaws with this tool for developers and security teams, producing exploit evidence and repair guidance.

Give an AI agent a real browser it can control with short commands: open pages, read them, click and fill forms.

For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.

Run supported language models and serve their answers to applications with a model-serving library for developers.

Install specialist helpers for code review, testing, security and Python or JavaScript work into your AI coding tool.

Let an AI coding assistant search your code, docs, logs and PDFs locally for the exact passage it needs.

WebCodex connects cloud-based AI chat tools like ChatGPT and Claude to a real development environment running on your own machine, so you can ask them to inspect a repository, modify code, run tests, use Git, or investigate a failure without moving your project into a hosted workspace first.

JEV-35B evaluates up to 256 options in one pass.

Ask yes-or-no, multiple-choice or rating questions about a piece of text, JSON, an image or a video, and get a probability for every allowed answer.

Use its Python encoder to format text and image chats, then run the model and get written replies.

Chat with a small text model that can call tools and give structured answers, for developers building local agents or specialized apps.

Send text, images or video and get written answers.

Ask questions about document images, pictures and video and get text answers; it needs NVIDIA GPU servers, so it suits developers.

Ask questions about one image, several images or a video and get text answers.

Ask a model questions about text or images and read written answers, through the Z.ai API or on your own servers.