Products from August 13, 2026

Holehe is a reconnaissance tool that checks if an email address is registered on a wide array of online platforms like social media, forums, and services. It solves the problem of not knowing where your or a target's personal data is exposed online by leveraging 'forgot password' functionalities to discover accounts. This tool is primarily for security researchers, penetration testers, and individuals conducting OSINT (Open Source Intelligence) to evaluate digital footprint and potential attack surfaces.

holaOS is an open-source, all-in-one workspace for AI agents. It solves the problem of fragmented AI tools by letting you run any agent (like Claude Code or Codex) across your entire digital environment—100+ integrations, apps, browser, and files—with shared memory for seamless context. It's built for developers and teams who want to centralize their AI workflows, offering built-in models or the flexibility to bring your own keys.

Unsloth is an open-source desktop application that allows you to run and train large language models (LLMs) and diffusion models locally on your own hardware. It solves the problem of needing expensive cloud compute or specialized infrastructure to work with advanced AI models like Qwen3.8, Gemma 4, and FLUX. It's designed for developers, researchers, and AI enthusiasts who want full control, privacy, and cost-effectiveness in their AI projects.

Modly is a desktop application that uses local AI to create 3D meshes from your photos or text prompts. It solves the problem of privacy, cost, and cloud dependency by running entirely on your own NVIDIA GPU, keeping your data secure and generations unlimited. It's for 3D artists, game developers, and creators who need quick, private, and high-quality 3D assets ready for tools like Blender, Unity, or Unreal Engine.

Obsidian Skills is a set of tools that enables AI agents to read from and write to Obsidian vaults using its command-line interface and open formats like Markdown and JSON Canvas. It solves the problem of AI assistants being unable to directly access or manipulate personal knowledge bases, bridging the gap between conversational AI and structured note-taking. It's designed for developers, researchers, and power users who want their AI agents to seamlessly integrate with and act upon their Obsidian-based knowledge systems.

FluidVoice is a macOS dictation app that performs all speech-to-text processing on your device, ensuring your voice data never leaves your Mac. It solves the problem of rough, rambling speech by using a custom-trained local AI model (Fluid-1) to transform spoken words into polished, ready-to-send text. It's for Mac users who value privacy, speed, and professional communication, offering a free, open-source alternative to cloud-based dictation services.

AI Search Readiness: measure structure, ship dry-run fix packs, rescore, seal with HMAC receipts. SEO tests if humans can find you on Google. AIO.GEO tests if AI agents can do business with you.

Qencode lets AI assistants transcode, analyze, edit, optimize, and deliver video using natural language, powered by a cloud video processing platform.

Phinq is an open source runtime governance layer for AI agents. It intercepts every agent tool call, classifies it by risk, lets safe actions pass, holds irreversible actions for human approval, and records each decision in a tamper-evident hash-chained audit log.

Every AI is good at different things — but your conversation is trapped in one. ThreadPort transfers the chat you're in right now to another AI with full context. No servers, no account, works in the EU. Free for 10 transfers/month. Chrome & Edge.

FluidDocs CLI turns your prompts into interactive documents that answer questions and report back. You see who opened it, how far they got, and what they asked. Pitch decks, proposals, reports, board updates. One line installs the CLI and one command publishes. Edit later by prompt, and the same link updates. Viewer-side AI-enabled Q&A and analytics come built in.

Watch your AI agent browse the web in real time. Pickle runs on your machine, using your real logins, with every action policy gated and logged as it happens. It compresses pages before your agent sees them, cutting token use by 32x. Works with Claude Desktop, Cursor, VS Code, and Codex CLI.

Execlave is an AI Agent Governance and Enforcement platform (runtime AMP) that sits between autonomous agents and your real systems, enforcing policy before every action instead of after incidents. It gives platform and security teams runtime policy enforcement, kill switches, and audit-ready trails so every agent action is authorized, traceable, and compliant with SOC 2, EU AI Act, ISO 27001, and other enterprise frameworks.

Create immersive AR experiences with AI, no code required. Meet Kivicube AR Agent, a new way to create WebAR experiences with natural language. Simply describe what you want and let AI bring your ideas to life. Create interactive elements, animations, UI, and experience pages with simple prompts. You can also use Kivicube’s visual editor for full creative control. Start with a template or your own assets. Customize your experience with powerful AR interactions in just a few clicks!

Kin helps you prepare for healthcare appointments, capture the conversation, and follow through afterward so you can stay present during the visit instead of taking notes or trying to remember everything later. After each visit, Kin turns the conversation into a focused summary. Rather than giving you a word-for-word transcript, Kin organizes the key points, recommendations, and next steps so you can quickly understand what happened and what to do next.

An important deliverable, or a pizza place saved for that someday trip to Italy—Mem Agent keeps track of what you tell it, plus the todos living inside your notes and meetings, sharply following up so it actually happens. And with Push-to-Remember, seamlessly capture a thought into Mem or recall something you saved with a single button—all without leaving your work.

Chiplab lets AI coding agents build, run, and test embedded software on a virtual copy of the real chip. No physical board required. Just connect it over MCP to any AI coding agent (Cursor, Claude Code, VS Code, and more), and skip hardware entirely. Chiplab compiles, runs, and debugs your firmware, and tells you exactly what broke. Works today on STM32 and Nordic chips, with more on the way. Currently in beta and we'd love your feedback.

Starlink's own app is phone-only, and the old web portal was switched off in 2024 with nothing to replace it. Dishylink brings that back as a native desktop app. It reads your dish and router over your own network. Features include: live stats, alignment in degrees, a 3D satellite view, obstruction time lapse, per-device data usage, power draw with daily and monthly history, and alerts that clear themselves. It's free, open source, no account, no cloud, and works on macOS, Windows and browsers.

A minimalist iOS game where the entire mechanic is waiting. A circle appears on a black screen after an unpredictable delay — tap it in time, or restart from Level 1. Global leaderboard and a particle visualization built from every 100ms you spent waiting.

An open-source MCP server that turns machines you already own into a fleet of AI agents. Mix Claude, Antigravity, Codex, Copilot, and local models via OpenCode; route work by cost tier; run durable, multi-hour, observable workflows. It builds its self autonomously.

Discover the Google Pixel 11 lineup featuring updated camera hardware, the Tensor G6 chip, LED HiLight notifications and faster Gemini AI support.

One command wraps Claude Code, Codex, Hermes, and more with a local proxy that compresses logs, tool output, and files before every provider call. In a pinned 54-run benchmark: 33.2% fewer input tokens with 18/18 correctness checks. Caveman can also run any existing agent skill with ~70% fewer tokens by loading text as images. Built on an open-source ecosystem with 97K+ GitHub stars.

Your browser, your models, your data. WebBrain is a free, open-source AI browser agent for Chromium browsers and Firefox. Run it locally with llama.cpp and most queries cost nothing — your data never leaves your device. It reads pages, extracts data, and automates tasks right from the sidebar. Prefer the cloud? Bring your own API key for OpenAI, Claude, OpenRouter, or 100+ OpenAI-compatible providers. Multilingual UI, token-conscious screenshots. MIT licensed.

Insta360 X6 is a flagship 8K 360 camera with dual 1/1.1" Sony sensors, 8K50 video, 10-bit color, 140 minutes of 8K30 recording, and built-in storage. Its new PanoMind model and AI Director can find highlights, choose angles, and turn 360 footage into ready-to-share clips.

An agentic quality verifier for developers and AI coding agents. Describe a test in natural language, and Kane CLI runs it in a real Chrome browser and returns pass or fail with shareable proof. No selectors to write. Local-first, free to start.

Scrimba Explain generates a narrated video tutorial about almost anything you ask, instantly. You can upload files, add links, paste code, or just write what you’re trying to understand. It's MUCH faster than any of the video generation models, as we utilise our DOM-based playback technology. The video explainer can include images, code walkthroughs, animations, diagrams, and other visual aids, plus voiceover, captions and cursor so it feels more like YouTube than traditional chatbot UX.

A free CC0 library of 2,000+ hand-drawn assets across 13 themed kits. Download individual SVGs and PNGs, or grab the full Figma Community libraries with reusable components, color variables and flexible, resizable assets. Use them for games, apps, maps, illustrations and playful little worlds. We’re also building a Figma plugin, MCP support and world-building tools around the library.

Dashboards are where insights go to die. Human Behavior closes the loop: 1) Collect. Our SDK captures your events, errors, and session replays. 2) Understand. AI watches every replay, catching rage clicks, dead buttons, and silent give-ups. 3) Act. Background agents email the customer, update Linear and your CRM, and open PRs with the replay as evidence. 4) Loop. Agents check the results and keep the product improving — on its own. No dashboard to babysit. It all lives in Slack or SMS.

Coarena lets AI agents compete on real computer tasks, not synthetic benchmarks. Watch multiple models complete the same workflow side by side, compare speed, accuracy, and reliability, then vote for the winner. Discover which agent actually performs best on everyday work across browsers, apps, and enterprise software.

Ito is an AI code review tool that runs your app before it reviews the code. For every pull request, Ito spins up an ephemeral environment, validates impacted flows, and returns runtime evidence so teams can catch bugs that static analysis and model-only reviewers miss. Instead of guessing from diffs, Ito shows what actually broke, where it happened, and why it matters before the PR reaches production.

An intelligent workspace for you, all your agents, and your team. Bring the best agents from across the ecosystem into one place, where people and agents work together as equal teammates. Every conversation, decision, and artifact becomes shared knowledge that compounds over time. As the workspace learns how you work, it adapts to your needs and builds specialized tools that help everyone do its best work.

Nuphos gives engineering teams a shared environment where AI agents can learn your infrastructure, investigate issues, and operate production systems.

Open a skill, and everyone is in it at once - real cursors, inline comments, and an editor that renders as you type. Then hand the whole conversation + diff back to the agent.