v0.21.0
Released 2026-11-05 · 3 min read · Omnigent maintainers
Omnigent 0.21.0 is a major release focused on making your agents' work easier to follow and act on, from reviewing pull requests inside a session to running that session on any machine you can reach. The Pull Requests panel is now a compact list with checks, merge actions and GitHub review threads you can work with inline. Chats now show tool calls as readable actions with per-file diffs. You can launch sessions over SSH straight from the desktop app. Side chats get their own model and effort controls, and deployments get more say in which agents and models New Chat offers.
1. Compact Pull Requests list with inline GitHub reviews
Keeping track of what your agent opened on GitHub shouldn't mean switching back and forth to the browser. The Pull Requests UI is now a compact list that shows each PR's checks and gives you merge actions in place. A session's linked PRs stay visible even while its host is offline, so you can still see where things stand when the machine running the session isn't connected.
Review conversations happen in the Changes view too. You can read and reply to GitHub review threads inline, or start a new one, right next to the code they're about. The composer also highlights PRs that need your attention, so you notice them before you send your next message.
Learn more in the Tracked pull requests.
2. Plain-language tool calls and per-file diffs
Scrolling through raw JSON to work out what an agent just did slows down every review. Chats now show tool calls as plain-language actions with a one-line result, so you can follow the agent's steps at a glance. When you need the details, expand a call to see labeled fields instead of a JSON blob.
File changes are clearer as well. Edits and new files show their line counts and a per-file diff, so you can check exactly what changed without leaving the conversation.
3. SSH sessions from the desktop app
Your code doesn't always live on the laptop in front of you. You can now run sessions on any machine over SSH and launch them straight from the desktop app. Pick the machine, start the session, and work with it the same way you would a local one.
Local sessions also fit more closely into your workflow. They can open localhost apps in the desktop browser pane, so you can watch the app your agent is building next to the chat. And when you want to take over a file yourself, the Files panel opens it in VS Code or Cursor.
Learn more in the Desktop App.
4. Model and reasoning-effort controls for side chats
A quick follow-up question doesn't always need the same model or effort level as your main task. Side chats now have their own model and reasoning-effort controls. You can send a side-chat follow-up to a different model, or turn the effort up or down, and the main conversation keeps its own settings.
Learn more in the Side chats.
5. Configurable New Chat agents and model picker
A long list of agents and models can make it harder to pick the right one. Deployments can now choose which built-in agents New Chat offers and which one it starts on, so every user sees the options that make sense for that deployment.
You can also tidy up your own view: hide individual harnesses and agents in Settings › Appearance. Long model lists now have a search box and are grouped by model creator, so you can find the model you want quickly.
Learn more in the Appearance settings.
Full Changelog: https://github.com/omnigent-ai/omnigent/blob/main/CHANGELOG.md
What's Next
Install or upgrade Omnigent:
curl -fsSL https://omnigent.ai/install.sh | sh