What shipped on the platform, and every new release of the agent templates you can deploy.
A file someone sends you now downloads instead of opening in the page, unless it is a photo, a PDF or plain text.
When another connected agent writes into one of your conversations, its messages are labelled as theirs, so your own history never reads as though you said something you did not.
Messages you queue while Nova is working stay in the order you typed them, and a queue you paused waits for you rather than emptying itself.
Messages you queue while Nova is working now go out one after another, each waiting for the last answer to finish. They used to leave together the moment Nova finished, and only the first one got answered.
Type while Nova is answering and your message waits in a list instead of disappearing. Send it straight into the answer being written, stop the answer and send it, or leave it and it goes on its own the moment Nova finishes.
Stop now really stops, instead of only clearing your screen while the work carried on.
Leaving a chat while Nova is answering no longer loses the reply. Come back and it is there.
Scheduled tasks now carry memory between runs, so a daily briefing knows what it already told you. Agents can also message each other directly, and long-running helpers can be steered or stopped mid-task.
Also: more models to pick from, tighter protection of the agent's own instruction files, and steadier Telegram connections that recover on their own.
Core v2026.8.31 · upstream notes.
Charts and diagrams now render right inside your conversations, and your agent starts up faster. Updates are safer too: if an update goes wrong, your agent rolls back on its own and keeps working with its configuration intact.
Plus a large batch of fixes across Telegram, WhatsApp, Signal, and the other channels.
Core 2026.9.1. See the upstream changelog shipped in the package for the complete list.
If Nova ever stops accepting your messages, it now sorts itself out and comes back on its own, instead of sitting there until someone restarts it.
Fixes an issue where updating your agent could occasionally fail. Plus small bug fixes.
Core v2026.8.27 · upstream notes.
Fixes an issue where changing your agent's model in the dashboard could appear to do nothing. Your agent now always follows the model you chose.
Core v2026.8.27 · upstream notes.
Reconnecting a channel with a fresh credential now brings it back straight away. Plus reliability improvements.
Core v2026.8.27 · upstream notes.
A messaging channel that stops working is now turned off cleanly while the rest of your agent keeps running. Your credential and settings are kept safe so you can restore the channel, and the channels list tells you what happened and when.
Core v2026.8.27 · upstream notes.
If one of your messaging channels stops working, your agent now keeps running. The channel shows as disconnected with the reason, and everything else carries on.
Core v2026.8.27 · upstream notes.
Fixes an issue where signing in to a connected tool could drop you on a login page instead of finishing. The agent's sign-in page has also moved; old links still redirect, so there is nothing to do.
Core v2026.8.27 · upstream notes.
A better model picker with new models to choose from, web search that works before you add any key of your own, PDF and file attachments, and smarter memory and scheduling.
Also fixes an issue where a Telegram connection problem could stop the whole agent. Your agent now stays up and simply shows Telegram as disconnected until you reconnect it.
Core v2026.8.27. Upstream notes: v2026.8.13, v2026.8.16, v2026.8.16.2, v2026.8.18, v2026.8.19, v2026.8.27.
Search past conversations by word or phrase, follow long-running work as it happens, and pin interactive results to a session dashboard. Audio and video now stay attached to the conversation, and there are more model providers to choose from.
Your agent also builds up long-term memory in the background, on by default. This background work uses a little of your credit; you can turn it off in your agent's settings.
Core 2026.8.1. See the upstream changelog shipped in the package for the complete list.
Ships upstream core v2026.8.27 (was v2026.8.3).
This release rolls up six upstream Hermes releases that had stacked up behind a stuck CI gate: v2026.8.13, v2026.8.16, v2026.8.16.2, v2026.8.18, v2026.8.19 and v2026.8.27 (Hermes Agent v0.20.1 through v0.20.6).
What you get
/model picker, a Ctrl+P command palette and a richer /status. New models across the pickers (GLM-5.3-Flash, MiniMax M3 free, MiniMax H3 Max video).Full detail is in the upstream notes for each release, linked below.
Compatibility
Nothing in this release changes how your agent is configured, and no action is needed on your side. Your existing settings, chat pairings and connected channels carry over untouched. We verified before shipping that the pairing store location and file format, the chat allowlist rules, the session header and the provider list all behave exactly as before, and the full wrapper contract suite passes against the new core.
Core v2026.8.27. Upstream notes: v2026.8.13, v2026.8.16, v2026.8.16.2, v2026.8.18, v2026.8.19, v2026.8.27.
The Files tab is now a full workspace: browse, rename, move, copy, upload, download, delete with undo, share links, and open files in place, with Markdown, CSV tables and images rendered. Works on a phone too.
Ask "how many" and Nova reads the whole document and counts every match instead of estimating. If a section can't be read, it tells you.
Nova now reads a document right through and answers exactly, at a fraction of the previous cost. Also fixes several ways a reply could quietly end without an answer.
Hand Nova several independent questions and it researches them side by side, then writes you one answer. Your budget is divided up front so parallel work can't overspend. Off by default per team.
Give Nova a goal and it keeps working on it between conversations, off by default per team. Your spending limits apply to every paid step, and every stop tells you which limit it hit and how far it got.
Follow along by RSS. The feed carries platform entries only.