1Password for Agents is a 1Password feature that lets supported personal and coding AI agents sign in to accounts without receiving or seeing the stored passwords. When an agent requests a credential, the person reviews and approves or denies the request on their own device; 1Password then fills the password or one-time code directly into the sign-in form, while credentials remain protected in the vault. It supports selected agent integrations rather than every AI tool, and availability and setup requirements vary by integration, account, region, device, and sign-in method. The feature is included with 1Password Individual and Families plans.
2G is a sampler instrument from Scrap Brain Audio inspired by early-2000s mobile phones. Its Neural Synthesis feature generates audio from text descriptions, after which samples can be trimmed, edited, tuned, and played from a keyboard. It analyzes timbre, volume, vibrato, and pitch to suggest loop points and correct detected tuning discrepancies, and provides controls for attack, release, brightness, detune, noise, quality, and formant. A physical model simulates the narrow frequency range and resonances of mobile-device speakers; its 16 kHz mono mode can be bypassed. 2G imports WAV, AIFF, FLAC, and MP3 files, which can be edited and played offline, while neural generation and credit verification require an internet connection. It is available as a VST3 or AU plug-in and as a standalone application for Windows and macOS.
AgentGrid.io is a shared workspace for humans and AI agents to work on the same live artifacts, including documents, reports, slides, apps, and designs. Users can work with agents such as Claude, ChatGPT, Codex, Hermes, OpenClaw, Cursor, and Grok Bot, then have an agent share an artifact into the workspace for people and other agents to access. The workspace provides shared context, per-agent and per-folder permissions for reading, writing, modifying, and publishing, plus version history and diffs for artifacts. Agents authenticate as agents, permissions can be revoked, approvals have owners, and revisions can be restored. The stated workflow is to work with an agent, ask it to share the resulting artifact on AgentGrid.io, and invite people or additional agents to collaborate on the latest version.
AI Bridge is a Mac app for running AI coding agents such as Claude Code, Codex, Grok and OpenCode in separate projects and workspaces. Each workspace has its own instructions, context files, repositories and automations, while the app tracks agent states such as working, needs you, ready and asleep and collects questions, approvals and other requests in an Inbox. It can also place Kubernetes clusters, databases and Slack channels beside the agents; database changes and Slack replies wait for approval before execution or posting. The agents remain the real command-line tools running in local terminals and use the providers and subscriptions already configured by the user. Projects, workspaces, instructions, automations and logs are stored as plain YAML and Markdown under a user-owned folder on the Mac. The page says code, conversations and agent work stay on the Mac, with no usage telemetry; the app checks its licence periodically after sign-in and checks for updates at startup. It is free to start, with paid plans adding additional clusters, database servers, Slack channels and scheduled automations.
Eleven Realtime is a family of speech-to-speech models from ElevenLabs for building voice agents. Its v1 Mini model is tuned for natural conversation, while v1 Max is designed for complex tasks; speech recognition, turn-taking, language-model behavior, and voice are optimized as one end-to-end system. It is available through ElevenAgents and an OpenAI-compatible Realtime API, with agents deployable to phone, web widgets, WhatsApp, and contact-center platforms. The videos describe it as supporting more than 90 languages.
FLUX 3 Max is a text-to-video and image-to-video generation model from fal Research and Black Forest Labs, post-trained by fal on FLUX 3 and served through fal's API and playground. It generates 720p video, including 10-second clips in about 12 seconds, using the same post-trained model for both text and image inputs. The model is available through fal's API with usage billed per second of output video and no subscription requirement. fal's page reports a preliminary image-to-video benchmark score of 1,139 Elo and describes the model as tied for the leading position in that evaluation.
Kiwi is a proactive AI assistant for iPhone and Android that reads a user’s calendar and email, tracks upcoming plans and obligations, and texts first when something needs attention. It can prepare or carry out tasks such as reminders, bookings, delivery changes, replies, and travel arrangements across services including Google Calendar, Gmail, Outlook, Slack, WhatsApp, Spotify, Uber, and websites; actions involving money or messages wait for the user’s approval, and prices are shown before payment. Kiwi reports an action as complete only after the relevant company confirms it, keeps passwords encrypted so its AI does not see them, and allows users to delete individual memories or their account. The service is free to use and is accessed through its app, Messages, or WhatsApp.
Llama is a free, open-source desktop app by the llama.cpp team and Hugging Face that runs open AI models locally on Mac and Windows computers. It provides a system-tray interface for chatting with models, recommends models and configures their llama.cpp settings for the host computer, and downloads models for local use. Models are stored in the shared Hugging Face cache, loaded on demand, and unloaded after an idle period. Llama also exposes a local API at localhost:9931 using OpenAI-compatible endpoints, with support for streaming, tool calling, structured output, and vision; the page also documents Anthropic-compatible endpoints. Coding agents, editors, chat applications, scripts, and other OpenAI-SDK clients can connect by changing their base URL, without API keys or usage charges. It can share models with llama.cpp and includes command-line installation and serving options. The app works offline, is distributed for Windows 11 and Mac, and is also available through package managers. The page describes a small native app and says that model files are downloaded separately rather than bundled with the application.
ManyAgents is a native macOS app for running teams of Claude Code and Codex coding agents in one window. Each project has an orchestrator that splits a request into tasks, opens agent tabs, and tracks their work. Workers build tasks in separate Git worktrees, thinkers handle difficult design or cross-codebase decisions, and read-only reviewers check completed work. It includes project and agent views, a built-in browser with signed-in browser takeover for testing web applications, an iOS Simulator panel for checking iPhone builds, and a needs-you view for agent questions and recommendations. It runs agents through the user's existing Claude Code and optional Codex accounts, keeping code on the Mac and stating that it has no analytics. Claude Code and macOS 14 or later are required; Claude Code requires a Claude subscription or Anthropic API key. The app offers a 14-day trial followed by a stated one-time license purchase.
Moli is an open-source headless browser engine built in Rust for AI agents. It fetches and extracts web pages, searches the web, and automates browser tasks while providing JavaScript, DOM, CSS, networking, storage, and browser automation capabilities. Moli treats the DOM as the source of truth and performs layout and rendering on demand, so DOM-first operations can avoid visual layout and paint. Layout enables geometry queries, coordinate input, screenshots, screencasts, and PDF output. It can be used through its CLI, CDP, WebDriver Classic, and WebDriver BiDi interfaces, including direct connections from Playwright over CDP, and supports Linux, macOS, and Windows.
Moli is a browser engine built from scratch for AI agents and agent harnesses, offered through Lexmount's cloud browser platform. It runs isolated browser sessions with proxy support and is designed for structure-first tasks involving DOM content, text, links, forms, network responses, layouts, and screenshots. Lexmount provides browser control through an API and SDK, alongside Web Search for finding relevant pages, Web Fetch for converting URLs into structured content, and Agent for delegating browser tasks and returning execution results. Moli can be tested in Lexmount's Playground and used with browser observability features such as live sessions, console output, network information, snapshots, and logs; capabilities vary by engine and session settings.
Monid Rankings is a live ranking resource for tools used by AI agents. It ranks tools by completed calls routed through Monid, with daily updates and views for the most-used tools, most-called endpoints, and fastest-growing providers across trailing usage periods. Monid describes itself as an OpenRouter for agent tools: agents can discover and use catalogued tools at runtime, while providers can contribute tools to its open-source project for inclusion in the hosted catalog.
MOVO AI is an autonomous AI video agent for long-form video creation. It takes ideas, scripts, references, and other assets through a conversational workflow: it interprets the creative direction, plans the story as scenes and shots, generates the video, supports review and refinement, and composes the selected material into a finished video. It maintains project context for characters, products, scenes, and visual styles to support consistency across videos and episodes, and is available on the web and mobile.
N8N Chat UI is a no-code service for designing branded chat widgets for n8n workflows and embedding them on websites. It supports floating or in-page widgets, live customization, file uploads with configurable file-type, size, and quantity limits, voice-message recording, responsive layouts, and real-time chat streaming enabled through n8n. The service can also connect Claude or another AI tool to its MCP server for natural-language widget customization, and offers plugins for Webflow, Wix, and WordPress.
Ovren is an AI coding agent for non-technical teams that turns natural-language requests into changes to an existing product connected through a GitHub App. It maps the project, sizes the task, proposes a plan for approval, and modifies a safe copy on a separate branch before opening a pull request for the team to review and merge. Frontend changes include a live preview, and each task includes an execution report describing what Ovren understood, which files it changed, and risks it identified. Tasks can be revised in the same pull request, with revisions supported up to five times, while the live product is not modified directly. The service works with Node.js, Vercel, Netlify, React, Vue, Stripe, Google Tag Manager, and SendGrid; GitLab and Bitbucket support is listed as coming soon. Project code is not stored or used for training.
ShogunAI is an AI assistant for Mac that keeps a private, encrypted work memory on the user’s computer. It uses email, meetings, documents, chats, calendar information and screen history to answer questions with source context, prepare for meetings, find previously seen information, and help resume work. The assistant can take meeting notes and produce recaps, decisions and next steps; show daily schedules and priorities; and draft follow-ups. Holding the right Option key in another application lets it continue text at the caret in the user’s voice, using relevant threads, documents and people as context, while drafts require confirmation before anything is sent. The site presents it as working alongside applications including Gmail, Notion, GitHub, Slack, Google Meet, Google Docs, Calendar, Dropbox and others, and offers a seven-day free trial for Mac.
sideOS is a macOS voice-controlled AI agent that lives in a MacBook's notch. Holding Control and Option, speaking, and releasing lets it read the live screen through macOS's accessibility tree, open or focus apps, click interface elements, type text, press key combinations, run AppleScript, and report what it did aloud. It can use local models or the user's API keys for supported AI providers, while on-device dictation requires no API request. The application also supports background tasks with shell commands, files, web search, page reading, PDF rendering, and AppleScript; it asks for approval before potentially irreversible commands and saves task output in a sideOS Tasks folder. Other functions described on its site include on-device meeting recording and transcription, reminders, app connections through MCP configurations, and optional local activity history. It is distributed as a macOS download with a one-time purchase.
Strawberry Browser is a desktop browser with built-in AI companions that work inside websites and accounts the user is already signed into. Users can hire official companions or create companions around defined workflows; companions learn user preferences and perform browser-based tasks such as researching leads and candidates, drafting outreach and replies in a user's voice, creating presentations and other visual materials from web sources, and turning meeting transcripts into summaries and follow-up actions. Recurring tasks can run on autopilot, creating tasks in services such as Linear, adding leads to HubSpot, or saving meeting notes in Notion. The product runs on macOS and Windows with a free tier.
SurgePix is an AI visual platform for generating images, presentation decks, carousels, and posters. It provides a layered, Photoshop-like canvas for editing individual elements, with exports including PPTX and PNG. The platform also offers agent skills and an image-processing API.
VibeiDE is a desktop command center for running coding agents across multiple projects. It runs Claude Code, Codex, and OpenCode tasks in parallel, queues work per project, and gives each task its own agent workspace or “desk.” Results wait for human review rather than being applied without approval. The app is presented for macOS and Windows, with a 14-day trial and no card required.
Searchable transcript of Top AI Agent Projects : VibeiDE, Strawberry, AI Bridge, ManyAgents & Moli by Lexmount — ManuAGI - AutoGPT Tutorials (18:30). Search for a phrase, then click its timestamp to jump straight to that moment in the video.
Captions sourced from the original video on YouTube, published by ManuAGI - AutoGPT Tutorials. The video, its captions and all related intellectual property remain the property of their respective owners; AINotes claims no ownership. Provided for research, accessibility and search — see the Transcript Notice and Copyright Policy.
00:00 Everyday developers build new AI tools and this is our weekly project update video. Top trending AI agent projects. This week you will discover trending AI tools and projects all in one quick video. Without wasting time, let's get started. Before we jump into today's project updates, here's a quick announcement for everyone. We've launched a brand new YouTube channel called AI Agent Studio dedicated entirely to AI Agent projects, tutorials, and tools.
00:27 So, if you're interested in staying up to date with the latest AI Agent open source projects, learning how to build your own agents, or exploring cuttingedge agent frameworks, make sure to check it out. Subscribe now to get weekly videos, in-depth guides, and realtime project breakdowns. The link is right there in the description. Don't miss it. All right, let's get into today's video.
00:52 >> Project number one, VIBED. Run coding agents in parallel. Review each. VIBED is a desktop command center for running coding agents across your projects. It solves the tab juggling of managing several agents in separate terminals where work stalls and results get lost. You bring your own clawed code, codeex, or open code and sign in with your own subscription.
01:13 And for each task, VIB opens a real terminal in the right project and starts your agent. You cue work across projects, so several agents run at once while the next task waits, and you watch them all in one view as an animated office or a batteryfriendly grid instead of switching windows. Each project keeps its own color-coded queue. Provider limits show at a glance, and one task maps to one session you can resume anytime.
01:38 Every result waits for your review before it is done since reviewing is the job now. Your task records stay on your computer and it never bills for tokens. It runs on Mac OS and Windows. It is built for developers and solo founders. Download it with a 14-day free trial. Project number two, 2G, a tiny neural sampler from text. 2G is a sampler instrument inspired by early 2000's mobile phones that generates sounds from a description.
02:05 It solves the hunt for the right sample, letting you make the sound in your head instead of digging through libraries. You describe a sound, its neural synthesis generates the audio, and you edit it and play it across your keyboard. It analyzes the sample for you, comparing tambber, volume, and VA to suggest up to three loop points for smooth sustained notes and measuring pitch to autocorrect tuning or mark a sample as unpitched.
02:29 You trim the start and end, shape, attack and release, and adjust brightness, d-tune, noise, quality, and formant. And a small speaker simulation models the narrow range and voice coil heating of a handset in 16 kHz mono. Switchable off. You can also import and edit your own wave, afflu, which uses no credits and works offline. Generated sounds are royalty-free for your music.
02:56 It runs on Windows and Mac OS as a VST3 AU or standalone. It is built for music producers. Get 2G free. Project number three, Nins. Surge Pix. Generate AI visuals then edit every layer. Surge Pix is an AI visual platform that generates images, decks, carousels, and posters. Then lets you edit every layer. It solves the dead end of flat AI output where changing one word or moving a logo means regenerating the whole image and losing the parts you liked.
03:27 You describe what you want and the AI generates it. Then it hands you a layered Photoshoplike canvas. Reward a headline, swap a chart, restyle one slide, or lock a product shot and logo in place while everything else changes. So edits stay contained and your brand stays consistent. It produces posters, presentations, CVs, diagrams, infographics, social posts, and banners and exports a finished publish ready result like PPTX or PNG with no design skills needed.
03:57 It also offers agent skills and an image processing API. So clawed code, cursor, codec or any skill MD agent can generate decks, remove backgrounds, translate on image text and inpaint. It is built for creators, marketers, and developers. Describe a visual and start. Project number four, Strawberry 1.0. A browser with built-in AI teammates. Strawberry is a browser with built-in AI companions that take real work off your hands.
04:26 It solves the copypaste grind of chat bots where you move answers between tabs, turn them into results by hand, and reexlain your work each time. Because it is a browser, it serves as a shared workspace. It sees what you are looking at and acts inside the accounts you are already signed into across all 1.8 billion websites, even behind login walls. Companions learn your habits and handle tasks end to end like sourcing qualified leads, enriching a spreadsheet from a thousand records, transcribing meetings without a bot,
04:58 building branded decks, and running recurring work on autopilot. You hire ready-made companions or build your own and it connects the apps your work runs on, carrying memory and context into the next task. It asks before irreversible actions, keeps passwords encrypted on your device, and meets SOC2 and GDPR. It runs on Mac OS and Windows with a free tier.
05:20 It is built for sales, recruiting, research, and founders. Download the desktop app free. Project number five, AIB Bridge. Run your coding agents like a team. AI Bridge is a Mac app that runs your AI coding agents like a team, each in its place with its own job. It solves the chaos of juggling several agents in scattered terminals where context bleeds between them and you lose track of which one needs you.
05:44 You organize work as projects and workspaces. So a project is the business with instructions that reach every agent and a workspace is one area of responsibility with its own rules, files, repos, and tools. So each agent already knows the job. Every agent is the real cloud codeex gro or open code CLI in a real terminal with a state bridge tracks working needs you ready or asleep and you pick any up tomorrow where it stopped.
06:12 One inbox gathers everything that asks for you. A grid keeps your key sessions on one wall and it puts your Kubernetes clusters, Postgress and MongoDB databases and Slack channels beside your agents with writes and replies waiting for your approval. Everything runs on your Mac as plain YAML and markdown you own with no telemetry. It is built for developers and their teams.
06:34 Join the wait list. Project number six. N8N chat UI. Custom chat widgets for N8N workflows. N8N chat UI is a tool for designing branded chat widgets for your N8N workflows and embedding them anywhere. It solves the limits of Nenaden's default chat widget, which looks generic, resists branding, and needs HTML, CSS, and JavaScript to change. You customize a widget in three steps with no code.
07:00 Style the bubble, tool tip, and window to match your brand. Connect it to your NADN workflow and copy paste it onto any site with changes shown live and a mobile friendly design by default. You can also customize it in plain language by connecting Claude or another AI tool to its MCP server. Widgets support file uploads with your own type and size limits, voice messages, and real-time streaming that turns on automatically when enabled in N8N and appear as a floating bubble or embedded in the page.
07:32 Ready-made recipes cover lead capture, booking, support, and knowledge bases with plugins for web flow, Wix, and WordPress. It is built for nade end users and makers. Design your widget free with 100 credits. Project number seven, many agents, many coding agents, one Mac window. Many agents is a native Mac app that runs a team of claude code and codeex agents at once.
07:54 It solves the sprawl of managing many agents in separate terminals where work collides and questions go unseen. You tell an orchestrator what you want and it splits the request into tasks, opens a tab for each and tracks who is doing what, running on the clawed code and codeex plans you already have, so there is no extra AI bill. Workers each build one task in its own git work tree, so they never trip over each other.
08:18 Thinkers are called in for hard design decisions, and reviewers check finished work readonly on a different provider to catch what self-review misses. Your app runs in a built-in browser beside the chat, where agents click through flows, fill forms, and test for you, or an iOS simulator for iPhone apps. Every decision an agent needs lands in one needs you list with its recommendation, and a card view shows each agent state with the ones waiting on you on top.
08:45 Code stays on your Mac with no analytics. It runs on Mac OS. It is built for developers. Download it free for 14 days. Project number eight, Miniax M3.1 Flash. Fast, lowcost model for agentic work. Miniax M3.1 Flash is a next generation flash model built for agentic tasks, coding, computer use, and cyber security. It targets the trade-off where capable models are too slow or expensive to run agents at scale, making online inference several times faster and cutting usage cost sharply against its predecessor.
09:18 It completes real enterprise workflows across SAS systems end to end handling sales, marketing, operations, support, finance, and HR, and holds up on multi-step planning, consistency across files and chain tool calls on software tasks. It independently understands code, builds features, fixes issues, and validates through testing across long sequences.
09:42 And it interacts with real environments to carry out cross application computer use tasks. It also audits code, patches vulnerabilities, and supports penetration testing and reverse engineering at low cost. More aggressive sparity drives its high output speed. It is available through the miniax API, the M plan, and miniax code with open weights to follow.
10:01 It is built for developers and teams running agents. Try it through the API or miniax code. Project number nine, Kiwi, a proactive assistant that texts you first. Kiwi is a proactive AI assistant that notices what needs doing and texts you before you ask. It solves the pull of small tasks, the flights, bills, replies, and birthdays that keep dragging you back to your phone and often wait until too late.
10:26 It reads your calendar and email to know what is coming up, then texts you once at the right moment with the small jobs already done. It reminds you before a call with the link, spots a delayed flight and offers to book a car for when you land or notices a free afternoon and offers to plan it. Say yes and it books orders and replies for you on any app or website, showing the price first and confirming only once the company does.
10:52 You stay in control. Anything that costs money or speaks for you waits for your yes. Passwords stay encrypted and unseen and nothing in an email or website can instruct it. It connects to Google Calendar, Gmail, Outlook, Slack, WhatsApp, Spotify, Uber and more. Reached in messages, WhatsApp or the app. It is built for busy people. Sign up in a minute.
11:13 Project number 10. Moly by Lex Mount. Cloud browser engine built for agents. Moly is a browser engine built from scratch for AI agents served through Lex's cloud browser platform. It solves the overhead of giving agents a browser where Chrome is heavy to start and run and the surrounding infrastructure is yours to maintain. Moly starts faster and uses less memory than Chrome and Lex mount runs isolated browser sessions with proxy support while handling the infrastructure.
11:41 You control sessions from your code and the platform pairs it with a web search API that turns a query into ranked links, a web fetch API that turns a URL into structured content and an agent product you delegate a whole browser task to. Moly suits structure first work like reading the DOM text and links, submitting forms and capturing screenshots. While Chromium is available for persistent contexts, extensions and compatibility sensitive tasks.
12:08 Live sessions are inspectable with console network and snapshot views and you connect over an SDK, the API, your coding agent or playright. It is built for developers building agents and web automation. Try it in the playground or create a free account. Project number 11, agentrid.io. Shared drive for humans and agents. Agentrid.io is a shared workspace where people and AI agents work on the same live artifacts.
12:36 It solves the scatter of handoffs where every exchange spawns another copy and nobody can say which version is current. Everyone, human or agent, works on one file in one place with shared context, controlled access, and full version history. So there is one source of truth instead of V26 final final passed around. You work with your agent wherever you already are.
12:57 Ask it to share the artifact whether a doc deck app or design and bring in your team and other agents who all open the latest version with the same context. Agents authenticate as agents and get scoped revocable permissions set per agent and per folder from read to write modify and publish. Everything versions and diffs like code identity travels with each suggestion and approval and every revision has a history.
13:23 It works with Claude, Chat, GPT, Codeex, OpenClaw, Hermes, Cursor, and more and is SOC2 secured. It is built for teams working alongside agents. Start your first shared artifact. Project number 12, Llama. Run Open AI models on your own PC. Llama is a free open-source app that runs Open AI models on your own computer. It lives in the system tray, picks models that fit your PC, and sets each one up automatically.
13:52 You can chat in your browser or connect coding agents, editors, and apps through a local API that works like open AIs. Models run offline so your data stays on your machine. Developers and privacy-minded users avoid API bills. Download it for Windows 11. Project number 13, One Password for agents. Agents log in without seeing your passwords. One password for agents is a secure login layer that lets personal AI agents sign in without seeing your passwords.
14:21 When an agent reaches a login screen, it asks for access. You approve or deny the request on your own device. Then one password fills in the password or one-time code directly and the agent continues its task. It works with supported agents like Muse and is included in individual and family plans. Join the wait list. Project number 14, Side OS, voice controlled AI agent in your Mac's notch.
14:46 Side OS is an AI agent that lives in your MacBook's notch and controls your Mac by voice. Hold two keys, say what you want, and it reads your screen, opens apps, clicks, types, and reports back. It works with Claude, Open AI, Gemini, or Grock using your own API key or with a local model offline. Dictation, meeting transcripts, and history stay on your Mac.
15:08 Mac users get hands-free work. Download it for Mac OS. Project number 15, Agent Hunt. Live rankings of the tools agents use most. Agent Hunt is a live ranking of the tools AI agents use most, powered by MONID. Tools are ranked by completed calls agents make through MONED, and rankings update daily. Moned lets agents discover, compare, and pay for tools at runtime with one integration.
15:31 Moned is open source. There are no per tools signups and no markup. Developers see which tools agents actually use. Explore the rankings. Project number 16, Moo AI. AI video agent for long- form storytelling. MOOA AI is an autonomous video agent that turns ideas, references, and assets into complete long- form videos through conversation. It writes scripts, builds storyboards, generates scenes, and assembles the final video.
16:01 It keeps characters, products, and styles consistent across scenes. It builds on models like Cance, Nano Banana Pro, GPT Image, and 11 Labs. Creators spend less time switching tools. Try it free on web or mobile. Project number 17. Verin AI coding agent for non-technical teams. Vernvir is an AI coding agent that ships changes to your existing product without waiting on developers.
16:27 You describe a task in any language, approve a plan, and Vern writes the code on a safe copy of your GitHub project. It opens a pull request with an execution report and a live preview of front-end changes. Your code is never stored or used for training. Non-technical teams ship small changes and developers review each one. Start free. Project number 18.
16:48 11 Labs Real Time. Speechto speech models for natural voice agents. 11 Labs Real Time is a family of speech-to-pech models that help developers build natural voice agents. It tunes speech recognition, turn taking, the language model, and voice as one system. Mini suits natural conversations and Max handles complex tasks and tool calls. You use it in 11 agents or through an open AI compatible real-time API.
17:15 Then deploy to phone, web or WhatsApp. It supports over 90 languages and zero retention mode. Build your first voice agent today. Project number 19 is Shogun AI private AI memory for your Mac work. Shogun AI is a private AI memory assistant for Mac that remembers your work across email, meetings, documents, and calendar. You ask what was decided and see where the answer came from.
17:40 It also takes meeting notes and writes replies in your voice. Memory is stored encrypted on your Mac, and only the context a request needs is sent to an AI provider. Founders and busy teams stop repeating themselves. Try the free trial. Project number 20, Flux 3 Max. Fast text and image to video generation. Flux 3 Max is a video generation model from Fail Research and Black Forest Labs.
18:04 It turns text prompts or images into video at 720p. A 10-second clip comes back in about 12 seconds. It is tied for first in imagetovideo quality on a preliminary artificial analysis ranking. Developers call it through the fail API. Switch models by changing one ID and paper second with no subscription. Try it in the playground. Thanks for watching.