Development Tools

Install once, document forever. Auto-updates all your documentation from your code so they never go stale.

Visual feedback annotation tool for developers to place markers on DOM elements and generate AI-optimized Markdown

Access your Cloudflare resources from the menu bar. Jump to any Cloudflare dashboard page in one click.

Most Mac cleaners work like a black box—you click "clean" and hope for the best. This one shows you exactly what it finds: file paths, sizes, and categories. You pick what goes, and everything moves to Trash. Terminal-based, open source.

Moshi lets you run coding agents like Claude Code from your iPhone. Agents need frequent input, but you can't always be at your desk. Moshi connects directly to your dev machine over Mosh — resilient UDP connections that survive network changes and device sleep. Speak commands with on-device Whisper instead of typing. One-tap shortcuts for Claude Code. Face ID for your keys. No cloud, no subscription — just you and your terminal.

Building AI chat features often means too much complexity — SDKs, databases, and infrastructure — just to support conversations and memory. Conversations API removes that overhead. Build stateful AI chat without managing backend systems. All chat data is stored for you — you only keep the conversation_id. What it helps with – AI chat memory & state – Faster prompt iteration – No backend setup – Ideal for low-code builders Built after helping builders stuck on AI chat infra instead of product.

Mistral OCR 3 extracts text and images from documents with SOTA accuracy. It handles handwriting, complex tables, and scanned forms, outputting clean markdown.

MiMo-V2-Flash is a 309B MoE (15B active) model by Xiaomi. It is a powerful, efficient, and ultra-fast foundation language model that particularly excels in reasoning, coding, and agentic scenarios, while also serving as an excellent general-purpose assistant for everyday tasks.

Varchive is a showcase of apps, websites, and experimental projects built with AI assistance, from passion projects to enterprise-grade apps. Varchive itself is built and maintained with assistance from Cursor and Codex. We've populated the archive with a few real-world apps—now it's time to submit yours.

Store and organize software binaries for any platform, with super accessible binary management which connects with the tools you already use. Whether you're working on mobile or desktop apps, games, or embedded - use Buildstash to share binaries securely with your team or with testers, guide builds through custom workflows, and distribute to users.

The Gemini Deep Research Agent is now available to developers via the Interactions API. Powered by Gemini 3.0 Pro, it autonomously plans, executes, and synthesizes multi-step research tasks.

Cursor’s new Visual Editor turns your browser into a live coding workspace. Drag, drop, and edit components visually, adjust props in real time, and describe changes with natural prompts bridging design and code in one seamless environment.

Bugster is a CLI that lets you create, edit, and run E2E tests seamlessly. Launch agents that explore your diffs in a real browser, uncover bugs and UX issues, and validate changes instantly.

The biggest update in 5 years. v5 brings a modular design, first-class quantization, and a new OpenAI-compatible serving API. Optimized for PyTorch and fully interoperable with the modern AI stack (vLLM, llama.cpp, GGUF).

Claude Opus 4.5 is intelligent, efficient, and the best model in the world for coding, agents, and computer use. It’s also meaningfully better at everyday tasks like deep research and working with slides and spreadsheets. Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.

Meta introduces SAM 3 and SAM 3D. SAM 3 segments and tracks objects in images and videos using text or visual prompts. SAM 3D reconstructs 3D objects and bodies from single images. Try them now in the new Segment Anything Playground.

Grok 4.1 is the new SOTA model from xAI, ranking #1 on the LMArena leaderboard. It features massive improvements in emotional intelligence, creative writing, and helpfulness, while also being 3x less likely to hallucinate than previous models.

Code with the latest frontier models from Anthropic, OpenAI and more. No credit card or API keys required. Instant access only for Product Hunt - https://cto.new/product-hunt

Kimi K2 Thinking is a new 1T parameter open-source agent model. It excels at reasoning, agentic search and coding. The model can execute up to 300 sequential tool calls. It features a 256K context window and native INT4 quantization for 2x speedup.

Termdock is a terminal‑centric AI dev environment that unifies multi‑workspace management, multi‑terminal layouts, and Git visualization in one interface. AST search (Tree‑sitter) lets you jump to symbols and dependencies instantly. Run up to 4 windows + PiP for Docker, Redis, logs, tests, and AI tools side‑by‑side. Drag‑and‑paste images to CLI, with large text auto‑compression. Built‑in file tree and prompt libraries keep workflows fast, consistent, and scalable.

gpt-oss-safeguard is a new family of open-source safety models (120b & 20b) from OpenAI. They use reasoning to classify content based on a custom, developer-provided policy at inference time, providing an explainable chain-of-thought for each decision.