AirJelly

AirJelly is an always-on desktop AI agent that its makers describe as the world's first context-aware proactive agent. It is aimed at people whose work moves faster than their notes, and its stated purpose is to bring scattered context together so that agents such as Codex and Claude Code can act with the full picture. According to the website, AirJelly reads across every app you use, including Slack, Zoom, Google Docs, Calendar and email, following the simple rule that if something is on your screen, AirJelly can see it. It is positioned as a second brain that organizes itself: the Product Hunt listing calls it a proactive, self-organizing second brain, while the site emphasizes that the agent knows who you are and what you are working on by observing your on-screen activity. 'The problem AirJelly addresses is context sprawl. The website frames it bluntly: you probably have twenty tabs open right now, and AirJelly is for anyone whose work moves faster than their notes. The fragments that matter — a confirmation in a team chat, a deadline mentioned in passing, a saved note you have forgotten about — get scattered across apps and rarely make it into a to-do list. Most AI assistants wait for you to ask before doing anything, which means the user still has to notice and remember. AirJelly's stated difference is that it watches your workflow continuously and acts before you ask, surfacing follow-ups, capturing tasks from conversations, and preparing briefs at exactly the right moment. It also tracks your personal interactions, so you never miss a follow-up or forget a promise. The product is built on three stated steps: watches, remembers and acts. Watching means capturing authorized screen context across your work apps, so the agent has visibility into the conversations, documents and meetings you actually work in. Remembering means building a living timeline of your work, where every task, meeting and message is searchable, forever. Together these two steps create the memory layer: a full log of everything AirJelly observed, across every app, which you can query at any time. The website describes this as moving from context to memory — gathering the scattered signals of a working day into one continuous record that does not depend on you writing anything down. Acting is the part users notice most. AirJelly surfaces what matters and then does something about it: it creates tasks, prepares briefs and sends reminders before you are asked, and its proactive alerts deliver follow-ups, reminders and briefs at what the site calls exactly the right moment. Because the agent has already watched and remembered the relevant context, an alert can arrive with the material attached — for example, a task created from a message, complete with due time and the conversation it came from. The company contrasts this with assistants that only respond to prompts, positioning AirJelly as a system that continuously works in the background rather than one that waits for instructions before it does anything at all. The website lists five core features built around how you work. The Daily Report is an end-of-day summary of what happened, what is pending and what comes next. The Timeline is a full log of everything AirJelly observed, across every app, so past work remains reviewable. Tasks are auto-captured from conversations, meetings and messages, complete with due dates and without the user writing anything down. Memory lets you ask about anything from your past work, anytime. Proactive alerts pull the other features forward by delivering follow-ups, reminders and briefs at the right moment. AirJelly's FAQ adds that task capture happens automatically from conversations, meetings and messages, with context and due dates included. AirJelly's overall approach can be summarized by the site's own progression: from context to memory, and then to action. The home page shows the loop as context for the agent, an activity log and deadline alerts, and it describes the mechanics in three numbered steps — watches, remembers, acts. One highlighted capability is bringing scattered context together so that Codex and Claude Code can act with the full picture. Practically, that means the agent converts your ongoing screen activity into structured context and memory, and then uses that memory to decide when a task, brief or reminder is warranted. The result is described not as a tool you operate but as an always-on companion that observes, retains and intervenes on your behalf. The stated outcomes are time and reliability. By managing everything in your life, AirJelly frees your time for what AI cannot do, or simply for you to enjoy. In practical terms, users get tasks that no longer depend on being written down, follow-ups that are not forgotten, briefs that are ready before a meeting, and a searchable record of past work that can be queried at any moment. The site groups the beneficiaries into four rough buckets: product, operations and engineering teams; founders and executives; researchers and PhD students; and anyone juggling more context than one brain can hold. The unifying benefit is that the user stops having to act as the memory system for their own work. AirJelly's site offers three concrete scenarios. In a product and operations setting, a meeting message became a task: the team confirmed a review in chat, and AirJelly caught it, created the task and attached the conversation, with the task created, the due time set and the context attached. In research and academia, fourteen tabs became one page: tabs spread across papers, docs and notes were read through and turned into a single research summary, including a note the user had forgotten they saved, with key points extracted and the past note surfaced. For founders and executives, an interview in thirty minutes was already prepared: AirJelly saw it on the calendar and prepared a brief with background, recent work and talking points. The FAQ adds that AirJelly also extracts tasks from conversations, meetings and messages automatically. AirJelly is a free download for Apple Silicon Macs and Windows x64 PCs, with Linux support described as coming soon. It reads across every app you use, with Slack, Zoom, Google Docs, Calendar and email named explicitly, and the rule that if it is on your screen, AirJelly can see it. Privacy is addressed directly: screenshots are encrypted and stored on your device, capture can be paused at any time, and specific apps can be excluded. The intended audience is anyone whose work moves faster than their notes — product, operations and engineering teams, founders and executives, researchers and PhD students, and anyone juggling more context than one brain can hold. There is also a Discord community linked from the site for users to join. AirJelly's pitch is simple to restate: instead of waiting for a prompt, an always-on desktop agent watches your workflow, remembers it as a searchable timeline, and acts — creating tasks, preparing briefs and sending reminders before you ask. For people whose work scatters across tabs, chats and calendars, that means less to remember and fewer dropped follow-ups. The product is available today as a free download for Apple Silicon Macs and Windows x64 PCs, with Linux support coming soon. The site's framing sums it up: stop asking, start working.