v0.23.0
Released 2026-11-19 · 3 min read · Omnigent maintainers
Omnigent 0.23.0 is a major release focused on making it easier to run, watch, and steer your agents, from automations that run unattended to reviewing the pull requests your agents open. Automations get more control: you can pick the MCP services each run can use, share an automation as read-only, and use a cheaper model for trigger polling. Session grids are now on by default, so you can watch up to four live chats side by side. Claude SDK and Claude Code native chats gain /rewind, and PR review now handles stacked PRs and lets you send inline comments to your agent.
1. More flexible Automations
Automations that run unattended should only touch the tools you meant them to, and they shouldn't cost much while they wait for something to happen. You can now choose which MCP services each automation run can use, so a scheduled job only gets the integrations it needs. When a trigger is polling for new work, it can use a cheaper model than the sessions it starts. You pay for the expensive model only when there is real work to do.
Automations are also easier to share. You can share an automation with others as read-only, and anything shared with you appears in a "Shared with me" tab. Automation instructions can now be up to 16,000 characters long, so you have room for detailed, multi-step instructions.
Learn more in the Scheduled tasks.
2. Session grids and workspace content search
When several agents are working in parallel, switching between tabs to check on each one gets old quickly. Session grids are now on by default. Drag sessions from the sidebar into a conversation to watch up to four live chats side by side.
Workspace content search is also on by default. Press Cmd/Ctrl+Shift+F to search across the contents of your workspace without leaving the app.
3. /rewind for Claude SDK and Claude Code chats
Sometimes you only see the better way to ask once the agent is a few turns down the wrong path. In Claude SDK and Claude Code native chats, type /rewind to go back to an earlier prompt, edit it, and resend it. You don't have to start a new conversation.
4. Inline review comments and stacked-PR diffs
Reviewing your agent's pull requests now fits better into the conversation. Leave local inline review comments on the diff and send them to your agent as chat context. The agent gets your feedback right next to the code it refers to, and you don't have to copy it into the chat yourself.
For stacked PRs, you can view only the changes made since one of the PR's commits. That way you can review each layer of the stack separately instead of reading the whole combined diff.
Learn more in the Inline comments and addressing.
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