Products from August 11, 2026

Switchy is a macOS menu bar app that automatically discovers nearby Macs on your local network, so you can connect to your magic devices without disconnecting and reconnecting or having to use a cable. It's useful for users who have multiple Macs or MacBooks (i.e work and personal) but want to use one set of magic accessories.

Run AI agents in the cloud — pick a machine, tell it what to do, close your laptop. Sessions resume from any device. Per-second billing, 21 models built in, no API keys. Solved 24/25 benchmark tasks — ahead of Claude Code and Codex.

AdmitRaven is a college counselor in your pocket for a fraction of the cost. It walks students through the entire application journey in daily, bite-sized lessons, and blocks doomscrolling until you finish them. It helps you craft authentic, compelling essays, stay on top of every deadline and requirement, and match to the right schools and scholarships. You can even read real admitted students' essays from your dream school, and ask them questions directly.

ScreenMark is a macOS menu bar app for live screen annotation, zoom, whiteboard overlay, freeze frame, and recording. Perfect for teachers, presenters, and developers. A free companion iPhone app turns your phone into a remote: trigger cursor highlight, flashlight, drawing and zoom. The free tier covers the core annotation tools. ScreenMark Pro unlocks recording, live zoom, cursor highlight and flashlight, advanced annotation, custom break-mode, custom shortcuts available in pro.

Instant dictation for desktop. Press a shortcut, speak, and instantly get accurate text on your clipboard—perfect for emails, coding, AI prompts, or brain dumps.

Lexi is the operating system for legal work. Legal teams use Lexi to draft, review, research, organize matter knowledge, and track every matter in one place, while lawyers stay focused on judgment, strategy, counsel, advocacy, and clients.

Continuum is a private Mac app for managers. You write down what you believe about each person you lead, tag what you notice in your 1:1s, and let your read change on the record. No scores, no reports, nothing that leaves your Mac.

Control your Android phone using natural language. Gotcha is a free, open-source on-device AI copilot featuring 100+ native device tools, dual safety modes, and real-time voice calls over any app, powered by Samosa AIR (LLM, STT, and TTS).

AMP autonomously monitors production logs, detects incidents, and opens a reviewable PR with the fix — no prompting needed. 80%+ fix rate. Certified for Java, Python, TypeScript, Node.js & Rust. No direct prod access. Human-in-the-loop. Use code PH3MOFREE.

Gitar reviews pull requests, diagnoses CI failures, applies fixes, and validates the changes against your pipeline. It can also retry flaky tests, automate review workflows, and act directly inside GitHub or GitLab. Now part of Sonar.

Kubit helps product engineers optimize AI agents with user behavior. Connect agent traces directly to user activities to see exactly why users re-prompt, drop off, or convert. Then, feed those insights straight into your coding agent to build AI products that actually stick. Start instantly with seamless integrations via OTel, your CDP, or Bring Your Own Warehouse (BYOW).

Cerenovus is the AI operating partner: it reads the records a company already produces and turns them into cited findings, live answers, and named deliverables.

Tines 3B is the single, secure environment for your most important agents, apps, and automation. Build with AI, from anywhere. Code runs isolated and credentials stay protected. Everything you ship is fully auditable and monitored from one place. Tines 3B is code-first and AI-native, built to help you move fast without compromising on security. Explore Edition is available today and gives you access to 3 live workflows with unlimited users, spaces, and connectors.

Run Claude Code, Codex, OpenCode, Gemini CLI, Grok and Pi in one tmux list with live status per session. space answers a blocked agent without attaching, f forks the conversation into a named sibling, T pins a plain shell next to the agents, and ctrl+r opens whole-file diffs where line comments go back as one review prompt. Sessions can spawn into their own git worktrees. Ordinary tmux sessions survive quitting the manager. One Go binary, Apache-2.0. macOS, Linux, Windows via WSL2.

Vizard Agent is a general AI video agent built to take on the whole video job. Start with raw footage, an existing video, a URL, a script, an image, or just an idea. Tell it what you want to make, and it figures out the work in between, from editing and generation to repurposing, localization, and revisions. Instead of managing a different tool for every step, you give one agent the outcome you want and work with it until the video is finished.

bb is an agentic orchestrator GUI, not unlike the Codex app, but it works with any provider: Claude Code, Codex, OpenCode, and more. What makes bb different is that it can customize and extend itself. Almost anything in bb can be changed with a single prompt. Ask for a task tracker, and one appears. bb also creates a skill that teaches all of your agents how to use it. Instead of waiting for your agentic workspace to add the feature you need, you can just ask for it.

The agentic development environment with institutional memory. Xirp connects to your services, ownership, docs, and architectural decisions so every session starts with real context. Powered by Spotify Portal.

Run AI agents in the cloud — pick a machine, tell it what to do, close your laptop. Sessions resume from any device. Per-second billing, 21 models built in, no API keys. Solved 24/25 benchmark tasks — ahead of Claude Code and Codex.

Bullet is a coding agent built for speed. We got tired of burning hours waiting on agent runs. The models were fine, but the loops around them were slow. Bullet auto-picks the right model/reasoning level per prompt, parallelizes searches/reads/commands, and uses targeted code search instead of embedding your whole repo. Works with your Claude Code or Codex subscription, API keys, or an on-device model. 95.8% on SWE-bench Verified (top 3), 119s/task. Built by Yale CS grads, ex-AppLovin/Citadel.

Equitybee Benchmark helps U.S. startup employees understand how their equity grants compare. Explore 9,000+ verified new-hire grants across 2,500+ startups by department, seniority, and company stage. For years, companies have benchmarked the equity they offer. Now you can benchmark yours. -- The benchmark provides market context based on Equitybee's dataset and is intended for informational purposes only. The dataset has not been independently verified. Data presented as is.

BetterClaw is a no-code platform for building AI agents that run on a schedule without you. Connect Gmail, Slack, or Telegram, and your agent triages inbox, sends morning briefings, or monitors what you care about. Agents start as Interns that ask before acting. Bring your own AI key and it's genuinely $0.