Omnigent Releases

November 2026

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

Choosing the MCP services an automation's runs start with

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.22.0

Released 2026-11-13 · 4 min read · Omnigent maintainers

Omnigent 0.22.0 is a major release focused on giving your agents more ways to start work and making it easier for you to keep up with them, from starting agent runs automatically on outside events to reviewing, steering, and organizing what they produce. Automations can now be triggered by Schedule, Jira, Slack, GitHub, Linear, or PagerDuty. The desktop app gets a native menu and a full set of keyboard shortcuts, and the pull request Changes tab becomes a proper review tool. The composer adds @ tagging. Sub-agents now nest in the sidebar, and a new AWS Lambda MicroVMs sandbox provider lets your sessions run, and fork, wherever you need them.

1. Automation Triggers for Schedule, Jira, Slack, GitHub, Linear, and PagerDuty

A lot of agent work starts with something happening somewhere else: a new ticket, a Slack message, an issue, an incident page, or a time of day. Automations can now be triggered by any of these. The available triggers are Schedule, Jira, Slack, GitHub, Linear, and PagerDuty, so the agent picks up the work when the event happens and you don't have to start each run yourself.

You pick the trigger right in the "New automation" form, and you can start a new automation from any session. This makes it easy to take a workflow you just worked through by hand and turn it into one that runs on its own.

Learn more in the Trigger templates.

2. Native Desktop Menu and Keyboard Shortcuts

If you spend your day moving between sessions, tabs, and workspaces, reaching for the mouse for every action slows you down. The desktop app now has a native menu and a full set of keyboard shortcuts for the actions you use most.

From the keyboard you can open new terminal and browser tabs and pin, archive, or fork sessions. You can also toggle the sidebars, switch between workspace tabs, reopen tabs you closed, and go back and forward. There's also an optional global shortcut that brings Omnigent to the front from anywhere on your machine, so your agents are one keystroke away.

Learn more in the Keyboard shortcuts.

3. Pull Request Changes Tab Review Tools

Reviewing a large agent-written pull request is hard when all you have is one long diff. The pull request Changes tab now has the tools you need to review in a focused, step-by-step way.

You can filter the list of changed files to find what you're looking for, and press Cmd/Ctrl+F to search for text inside the diff. As you go, you can mark files as viewed and track your progress through the change. You can also browse each commit's diff separately and follow how the change was built.

Learn more in the Tracked pull requests.

4. @ Mentions and Message Editing in the Composer

Giving an agent the right context shouldn't mean copying and pasting session names or file paths. Type @ in the composer to tag sessions, sub-agents, and files directly in your message.

If you sent something too early, you can edit a sent message back into the composer and revise it instead of retyping it. Agent replies can also show screenshots saved in the workspace, so you can see what the agent saw without opening the file separately.

Learn more in Mentioning sessions and files.

5. Nested Agents in the Sidebar

When one agent starts several others, a flat session list fills up fast and it's hard to tell which session belongs to which. With nested agents, the left sidebar now groups related sessions together.

Agents spawned through the omnigent MCP, or created on the same managed sandbox, appear nested in the sidebar. You can see at a glance how your work is organized and jump straight to the sub-agent you need.

6. AWS Lambda MicroVMs Sandbox Provider

Omnigent adds a new sandbox provider, AWS Lambda MicroVMs, which gives you another option for running agent sessions in isolated cloud environments. If your network requires it, sandbox traffic can now go through upstream HTTP proxies.

Sessions are also easier to move. Sandbox and managed sessions can fork to any host or sandbox provider, so you can take a conversation and continue it in whichever environment fits the next step.

Learn more in the Cloud Sandbox Host.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

October 2026


v0.20.0

Released 2026-10-28 · 3 min read · Omnigent maintainers

Omnigent 0.20.0 is a major release focused on keeping your whole workflow inside Omnigent, from where your agents run to how you review and ship what they produce. You can now merge, edit, label, and review pull requests without leaving the Pull Requests tab. Databricks Sandboxes can run as managed hosts under your own Databricks account. A new /mcp command shows which of a session's MCP servers are connected. Alongside these come composer shortcuts such as /clear, Shift+Tab, and prefilled ?prompt= links, plus a chat view where shell calls look like a terminal and file links open exact line ranges.

1. Pull request actions in the Pull Requests tab

Editing a pull request's title and description in the Pull Requests tab

When your agent opens a pull request, the last steps shouldn't send you off to another tab. You can now do that work in the Pull Requests tab itself: merge the PR or turn off auto-merge, edit its title and description, add or remove labels, request or withdraw reviewers, and post comments.

Open the Pull Requests tab, pick the PR you're working on, and use the controls there to finish the job. Everything from a quick label change to the final merge happens next to the session that wrote the code.

Learn more in the Tracked pull requests.

2. Databricks Sandboxes as managed hosts

Running agents in a cloud sandbox usually means setting up SSH or putting a shared credential inside the box. Databricks Sandboxes can now be managed hosts, and you don't need either of those.

Each Sandbox is created and run as you, through your Databricks account connection. Neither SSH nor a shared credential goes into the Sandbox, so your agents run with your own identity and permissions.

Learn more in the Databricks section of the cloud sandbox configuration reference.

3. The /mcp command

The /mcp panel showing a connected server, servers that need sign-in, and a local server

When a tool call fails, you shouldn't have to guess whether the MCP server behind it is up. Type /mcp in the composer to see the session's MCP servers and whether each one is connected.

If a service or host server needs you to sign in, a Sign in button appears inline. You can fix the connection right there and get back to the conversation.

Learn more in the Authentication section of MCP & Tools.

4. Composer shortcuts: /clear, Shift+Tab, and ?prompt= links

Several common actions are now quicker from the composer. In Claude Code and Codex sessions, you can run /clear from web chat to start fresh without switching to the terminal. In native sessions, press Shift+Tab to cycle through permission modes, so changing how much the agent can do without asking takes one keystroke.

To start a new chat with text already filled in, use a link with a ?prompt= parameter. This is handy for bookmarks, docs, or sharing a ready-to-run request with your team.

Learn more in the Keyboard shortcuts section of the Web UI docs.

5. Terminal-style shell calls and line-range file links

A shell call shown like a terminal, with the command and its output

Long agent sessions are easier to follow now. Shell calls look like a terminal: you see $ command, then its output and exit status, so you can scan what ran and whether it worked.

File links can point to a line range such as file.ts:10-20 and open straight to it. Agents can also use ui_open_file to open a workspace file in your session, so they can show you the code they're discussing instead of only describing it.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.19.1

Released 2026-10-21 · 1 min read · Omnigent maintainers

Omnigent 0.19.1 is a security-focused patch release. It contains no new features. It updates Omnigent's dependencies to mitigate the impact of the recent eMudhra Intermediate CA Compromise. We recommend upgrading to 0.19.1 so your installation picks up the updated dependencies.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.19.0

Released 2026-10-20 · 3 min read · Omnigent maintainers

Omnigent 0.19.0 is a major release focused on giving your agents safe access to the tools and code they need and making their work easier to steer, from connecting managed MCP tools and private Git repositories to tuning, editing, and reviewing what your agents produce. On servers with an MCP registry, you can now connect managed MCP accounts and route their tools through a server gateway with shared policy checks. Sandboxed agents can work with approved Git repositories over SSH without ever holding the key. You can also set reasoning effort for SDK agents from the web composer, edit custom agents right in Settings, and see much more review context in the Pull Requests panel.

1. MCP Registry and Gateway

Choosing MCP services before launching a session

Wiring MCP tools into every agent by hand gets old fast, especially when the same accounts need to work on your laptop and in a sandbox. If your server has an MCP registry configured, you connect managed MCP accounts once, in Settings, and then choose which of their tools your agents can use.

Those tools go through a server gateway whether your agent runs on a local host or in a sandbox. Because every call passes through the gateway, the same policy checks apply wherever the agent runs.

Learn more in the MCP servers.

2. Custom Agent Editing in Settings

Editing a custom agent's description, harness, model, instructions, and MCP servers in Settings

Changing a custom agent shouldn't mean rebuilding it from scratch. You can now edit your custom agents directly from Settings and adjust their configuration in place.

If you manage agents from code, a conditional PATCH API lets you update individual settings without resending the whole configuration.

Learn more in the Custom Agents.

3. Reviewers and Comments in the Pull Requests Panel

Pull Requests panel showing reviewer states, checks, and the separate Comments tab

Following a pull request used to mean switching back to GitHub to see who still had to review it and what people had said. The Pull Requests panel now shows pending reviewers and review states, so you can tell at a glance where a PR is stuck.

Comments now have their own Comments tab with a count, so new feedback is easy to spot. In conversation comments, each author gets a different color, which makes long threads easier to follow.

Learn more in the Tracked pull requests.

4. Reasoning Effort for Claude SDK and Codex SDK Agents

Some tasks need careful thought and others just need a quick answer. Until now you could only set reasoning effort in native terminal sessions. Now you can also set it for Claude SDK and Codex SDK agents.

Pick the effort level in the web composer, next to where you type your message. You don't need to restart anything or switch to the terminal.

Learn more in the Reasoning effort.

5. SSH Git Access for Sandboxed Agents

Sandboxed agents often need your private repositories, but copying your SSH key into a sandbox gives up the isolation the sandbox is there to provide. With this release, sandboxed agents can use approved Git repositories over SSH and never receive the key.

You decide which repositories are approved. Push access is optional and set per repository, so an agent can read one repo and push to another, with each permission granted on purpose.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.18.0

Released 2026-10-13 · 3 min read · Omnigent maintainers

Omnigent 0.18.0 is a major release focused on making Omnigent the home base for all of your agent work, from reviewing code wherever your repos live to catching up on everything your agents have said while you were away. The session panel now reviews GitLab merge requests and Azure DevOps pull requests alongside GitHub, a new omnigent agent add command installs reusable custom agents that follow you across hosts, Settings → Harnesses shows you exactly what each harness loads at startup, and a redesigned Inbox with All, Unread, and Awaiting response tabs makes it easy to find the replies that need you.

1. GitLab and Azure DevOps review in the session panel

GitHub, GitLab, and Azure DevOps review panels with example data on desktop and mobile

Not every team keeps its code on GitHub, and until now that meant the session panel's review workflow only covered part of the picture. Omnigent 0.18.0 brings GitLab merge requests and Azure DevOps pull requests into the session panel with the same treatment GitHub pull requests get: checks, comments, and diffs, all right beside the conversation that produced the change.

Tracking is automatic. When an agent creates or updates a merge request or pull request during a session, Omnigent picks it up and shows it in the panel, so you can review what the agent shipped, read the discussion, and watch checks land without leaving the session or switching between three different code hosts.

Learn more in the Tracked pull requests.

2. Reusable custom agents with omnigent agent add

Custom agents are most useful when you can reach for them again and again, not just on the machine where you first wrote the config. Omnigent 0.18.0 adds a small CLI for exactly that: run omnigent agent add to install a reusable custom agent, omnigent agent list to see what you have installed, and omnigent agent remove to clean up the ones you no longer need. If you built an agent with Create custom agent, you can import its bundle directly.

Once installed, an agent stays in your new-session picker across hosts, so the same agent you tuned on your laptop is one click away when you start a session on a shared server or a cloud sandbox.

Learn more in the Custom Agents.

3. Harness inspection in Settings → Harnesses

Claude Code harness details with MCP servers, skills, plugins, and startup settings

When an agent behaves unexpectedly, the first question is usually "what did this harness actually load?" Settings → Harnesses answers it. For each harness, you can browse the MCP servers it connects to, the skills and plugins it discovers, and the startup settings it launches with, all in one place in the UI.

That makes it much faster to confirm a new MCP server or skill is wired up before you start a session, or to spot the missing plugin behind a tool call that never fires, without digging through config files on the host.

4. Inbox tabs and sidebar reordering

Inbox with All, Unread, and Awaiting response tabs and cards grouped by recency

Running several agents at once means replies pile up faster than you can read them. The Inbox in Omnigent 0.18.0 is built for catching up: switch between All, Unread, and Awaiting response tabs to focus on the sessions that actually need you, and expand cards grouped by recency to read a reply in place before deciding whether to jump into the session.

The sidebar gets more flexible too. You can now drag pinned sessions to reorder them, so the sessions you care about most sit exactly where you expect them.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.17.0

Released 2026-10-06 · 3 min read · Omnigent maintainers

Omnigent 0.17.0 is a major release focused on making everyday work on a shared server smoother and safer, from signing in to the desktop app in the first place to keeping agent spend within a budget. Headline additions include browser-based OIDC sign-in with silent renewal for the desktop app, a set of keyboard shortcuts that let you move between workspace tabs, views and recent sessions without reaching for the mouse, and policies that can now enforce period-based cost budgets with richer per-event context.

1. OIDC sign-in through the system browser in the desktop app

Signing in to a company-run Omnigent server should feel like signing in to any other SSO-protected app, not like configuring a client. The desktop app now hands OIDC sign-in off to your system browser, so you authenticate with your identity provider in the browser you already use, and the app picks up the session from there. Once you are in, tokens renew silently in the background, so you are not bounced back to a login screen in the middle of a session.

The flow supports public PKCE clients and lets you specify explicit provider endpoints when discovery alone is not enough for your identity provider. Operators can also set a server name that the desktop app shows next to each host, so when you work across several servers you can tell at a glance which one you are connected to.

Learn more in Single sign-on (OIDC).

2. Keyboard shortcuts and a more scannable sidebar

Driving an agent is faster when your hands stay on the keyboard. This release adds shortcuts for switching between workspace tabs, jumping to common views and reopening recent sessions, plus Ctrl+Shift+L to put the cursor straight back in the chat input from anywhere in the app. Together they make the move from reading a diff or a file to telling the agent what to do next a single keystroke.

The sidebar's agent hierarchy has also been reworked to be easier to scan, so parent sessions and their sub-agents are clearer at a glance. And when you archive a session that was working on its own worktree, you can now choose to delete that worktree at the same time instead of cleaning it up by hand later.

Learn more in Keyboard shortcuts.

3. Period-based cost budgets and richer PolicyEvent context

Capping what a single session can spend is useful, but most teams think about spend per day or per week rather than per conversation. Policies can now enforce period-based cost budgets, so you can set a limit for a window of time and have Omnigent ask before crossing the thresholds you set and block expensive models once the limit is reached, without watching a dashboard.

Custom policies also get more to work with. The PolicyEvent context now carries the conversation_id, so a policy can key its decisions and state to a specific session, and RESPONSE-phase checks receive a turn_final indicator that tells you whether the response you are inspecting is the last one in the turn, letting you reserve expensive or conclusive checks for the moment the agent is actually done.

Learn more in Built-in policies: per-user period budgets and the PolicyEvent reference.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

September 2026


v0.16.0

Released 2026-09-29 · Omnigent maintainers

Omnigent 0.16.0 updates the workspace browser, sandbox controls, and agent configuration. It also improves runner reconnection and harness reliability. Review the breaking changes below before upgrading.

Major new features

Unified workspace browser and file panel

A unified workspace browser and compact file panel show badges for added, modified, and deleted files. Shared controls and folder indicators make changes easier to find while navigating the workspace.

The desktop app adds Show in Finder for local files and an opt-in setting to open chat links in the in-app browser. Embedded browser sites can request local network access through a Chrome-style permission prompt.

The unified workspace browser

(#8254, #8335, #6691, #8219, #8049, @ajayalfred, @nakazax, @fanzeyi)

Sandbox edits and repository clones

Linux agents can make disposable edits by setting copy_on_write: true on a sandbox write_paths entry. Edits stay in a disposable layer while the underlying files remain unchanged.

Admins can opt into shallow clones to limit history or blobless clones to fetch file contents on demand. Daytona sessions also keep their workspace when a stopped or archived sandbox resumes.

Learn more about filesystem access and Git clone options.

(#7599, #8322, #7828, @mxatone, @dhruv0811, @wilbeibi)

Admin defaults for sharing, allowed origins, and Slack setup

Settings > Sharing now lets admins default new sessions to public, choosing off, sandbox-only, or all sessions.

OMNIGENT_WS_ALLOWED_ORIGINS accepts *. entries to trust all subdomains of a domain. Operators can also pre-select the Slack setup agent and managed host through OMNIGENT_SLACK_DEFAULT_AGENT_ID and OMNIGENT_SLACK_DEFAULT_HOST_TYPE; users can change those choices before submitting setup.

Settings > Sharing with the default visibility controls

Learn more about session sharing and Slack setup defaults.

(#8295, #8070, #6965, @dhruv0811, @natsuskaizen, @bdchatham)

Pi prompt controls and native images

Pi agents can set executor.context_files: false to skip automatically discovered context files while keeping their explicit instructions. With the regular Pi harness, executor.system_prompt_mode: replace replaces Pi's base system prompt with the agent's Omnigent instructions. Framework instructions remain in place, and skills and extensions can still contribute to the final prompt.

MCP tool images and embedded-browser screenshots now reach supported harnesses as native images with accompanying text.

Learn more about the system prompt.

(#8184, #8349, #7444, @PattaraS, @Jomak-x)

Breaking changes

  • Saved preferences and inference snapshots are now capped at 65,535 stored bytes: upgrading resets oversized preferences to defaults and clears snapshots that remain oversized after compression, and new oversized project-order saves or snapshots are rejected before session creation (#8137, #8143, @dbczumar)
  • Only session owners can manage MCP servers or replace agent bundles; collaborators who previously edited MCP configuration now get read-only visibility and must ask the owner to make changes (#8481, @dhruv0811)

Bug fixes

  • 🔌 Brief runner drops (Wi-Fi roam, VPN stall, sleep/resume, replica failover) no longer fail turns with "Runner disconnected unexpectedly", runners reconnect promptly, and host launches no longer spawn duplicate runners (#8093, #8094, #8152, #8413, #8085, @yaoharry, @dbczumar, @daniellok-db)
  • 🖥️ Codex terminals recover without restarting a healthy backend, keep their final screen and exit code, survive launcher sign-in prompts with the link shown in chat, and cold resumes no longer lose tool results across compaction; sub-agents no longer flash "failed" on newer Codex versions (#7442, #8233, #8040, #8271, #8309, @yaoharry, @dbczumar)
  • 🤖 Claude Code sessions use a Unix socket instead of a loopback port per MCP helper, treat /exit as a clean stop, show Claude's own API error text, aren't failed by a background sub-agent, and mark lost messages undelivered instead of duplicating the next one (#8079, #8364, #8097, #8103, #8186, @dbczumar, @yaoharry)
  • 🧠 Pi on the Databricks AI Gateway lists Claude, OpenAI, and Gemini models, sub-agents no longer report false launch failures, and new sessions accept the first message during provider setup (#8228, #8200, #8424, @dbczumar, @serena-ruan)
  • ✍️ Composer fixes: cancel or edit an unsent message while a model switch finishes, pick skills with / anywhere in a prompt, and Files panel search finds tracked files in repositories of any size (#8039, #8087, #8409, @dbczumar, @serena-ruan)

Desktop onboarding preview

We're working on a redesigned desktop onboarding flow to make setup easier for new and returning users. This preview is still in development and hasn't shipped in a desktop release yet.

We'd love to hear your thoughts on the new flow and what would make getting started smoother. Share your feedback on Discord.

Preview of the redesigned desktop onboarding flow

(#8119, #8126, #8195, #8202, #8290, #8277, #8311, @hzub, @zhengwin)

Other contributions

#8055, #8072, @ajayalfred; #5917, @Arshgill01; #7495, @arthivjkumar; #8439, @chameleon82; #8485, @christianclaudio; #8002, #8029, #8066, #8108, @daniellok-db; #8042, #8053, #8063, #8074, #8090, #8092, #8138, #8270, #8320, #8362, #8416, #8469, #8494, @dbczumar; #7802, #8327, @dependabot[bot]; #8216, #8313, #8316, #8319, #8325, #8330, @dhruv0811; #7871, #7872, @dipeshbabu; #2405, @dosenr; #7977, #8041, #8051, #8056, #8057, #8059, #8061, @fanzeyi; #8017, #8026, #8031, #8106, #8132, #8201, #8444, @hzub; #8140, #8146, #8149, #8247, @Leemoonsoo; #6770, @nhsdb; #5519, #7166, #7479, #7512, #7602, #7673, #7698, #7704, #7708, #8014, #8166, #8196, #8403; #8028, #8035, @omnigent-ci[bot]; #7991, #8114, #8192, #8206, #8207, #8262, #8275, @PattaraS; #8024, #8025, #8098, #8113, #8117, #8120, #8158, #8178, #8185, #8197, #8256, #8417, #8425, #8428, #8431, #8432, #8510, @serena-ruan; #8160, @terrytangyuan; #8351, #8410, @TomeHirata; #7731, @trungnguyen21; #8046, @tyler-lynch; #8215, @vasvlasov; #7975, #8006, #8058, #8095, #8096, #8240, #8260, #8263, #8266, #8503, @yaoharry; #8062, #8081, #8110, #8118, #8136, #8141, #8159, #8161, #8162, #8163, #8174, #8179, #8182, #8191, #8193, #8194, #8198, #8220, #8221, #8222, #8223, #8224, #8225, #8226, #8236, #8255, @zhengwin

💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our Discord! Thank you for building omnigent with us, keep the bug reports, ideas and contributions coming :)

@ajayalfred, @Arshgill01, @arthivjkumar, @bdchatham, @chameleon82, @christianclaudio, @daniellok-db, @dbczumar, @dependabot[bot], @dhruv0811, @dipeshbabu, @dosenr, @fanzeyi, @hzub, @Jomak-x, @Leemoonsoo, @mxatone, @nakazax, @natsuskaizen, @nhsdb, @omnigent-ci[bot], @PattaraS, @serena-ruan, @terrytangyuan, @TomeHirata, @trungnguyen21, @tyler-lynch, @vasvlasov, @wilbeibi, @yaoharry, @zhengwin

Full Changelog: https://github.com/omnigent-ai/omnigent/blob/main/CHANGELOG.md

Install or upgrade

curl -fsSL https://omnigent.ai/install.sh | sh

v0.15.0

Released 2026-09-24 · 4 min read · Omnigent maintainers

Omnigent 0.15.0 is a major release focused on the everyday session experience, bringing a new native harness, lots of quality-of-life features for session management, and improved chat UX within sessions. Here are some of the highlights:

1. Devin as a native harness

The real Devin TUI mirrored into the Omnigent web UI, writing a Rust hello-world script alongside the working-folder panel

Running a coding agent through a translation layer means losing the details of its own interface. Devin now runs as a native harness in Omnigent: omni devin mirrors the real Devin TUI into the web UI, the same way the Claude Code and Codex native harnesses do, so what you see in the browser is the actual Devin experience rather than an approximation of it.

The previous ACP-based Devin harness is replaced by the native one. The old harness id continues to resolve, but sessions now run through the native path, so existing configurations keep working without changes.

Learn more in the Devin.

2. Curated model catalogs for Pi, custom ACP agents, and managed sandboxes

New session composer showing the selected Pi model with a tooltip naming the harness, model, and gateway connection

Picking a model should not mean scrolling through every identifier a gateway happens to expose. Pi, custom ACP agents, and managed Kubernetes / Agent Sandbox sessions can now show configured model shortlists, so your team sees the handful of models you actually want them to use.

Catalogs are configured per harness, each with its own gateway, and you can optionally turn on live gateway discovery to populate the list from what the gateway currently serves instead of maintaining it by hand.

Learn more in the Choose a model.

3. A richer Composer

Typing '/plan' in the Composer to discover and insert the skills available to the session

The Composer is where you spend most of your time in a session, and this release makes it do more. You can preview attached images before you send them, and Claude Code and Codex sessions accept more types of files as attachments. Queued messages and active sub-agent work are now managed directly from the Composer, so you can reorder, edit, or check on in-flight work without leaving the input.

Skills are also easier to find: from the new session page, type / (or $ for Codex) to discover and insert the skills available to that session.

Learn more in the Multi-modal input.

4. Side chats

A side chat answering a question in the right panel while the main session transcript stays untouched

Sometimes you want to ask a quick question about what the agent is doing without steering the main conversation off course. Side chats give you a separate thread inside your session: the side chat sees the context from your session, but nothing you discuss there is added back to it, so your primary transcript stays focused.

To start one, use the "+" button in the chat pane's right panel.

Learn more in the Side questions with /btw.

5. Improved session management

As your session list grows, keeping it organized matters. You can now export a session straight from its actions menu, arrange projects in the order you want rather than the order they were created, and see pull request titles in the session PR dropdown instead of bare numbers, making it easier to tell at a glance which PR a session is tracking.

Learn more in the Session management.

6. Reverse-proxy subpath deployment with --base-path

Not every deployment gets its own hostname. Omnigent can now serve the web UI and API behind a reverse-proxy subpath, so you can mount it alongside other internal tools under a shared domain. Set OMNIGENT_WEB_BASE_PATH or pass omnigent server --base-path and both the UI and the API resolve correctly under that prefix.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.14.0

Released 2026-09-15 · 3 min read · Omnigent maintainers

This release makes it easier to work across GitHub repositories, configure sessions, and keep track of ongoing work. It also adds deployment options and improves session recovery.

Work across repositories

  • Track multiple GitHub PRs in one session, including PRs from different repositories.
  • Switch between PR summaries and diffs, and manually link or unlink PRs.
  • Start a managed sandbox with multiple GitHub repositories: choose repositories and branches when creating a session; Omnigent clones them in parallel so the agent can work across them.

A smoother chat interface

  • Configure sessions in one place. The redesigned composer brings workspace, agent, model, reasoning effort, and permission controls together, with improved folder browsing.
  • Find sessions faster. Search session names with ⌘⌥S on macOS or Ctrl+Alt+S on Windows/Linux.
  • Open the model picker from your keyboard with ⌘⇧M on macOS or Ctrl+Shift+M on Windows/Linux.
  • Inspect running background commands from a compact badge beside the composer's workspace controls.
  • Manage context in Claude SDK sessions. See context-window usage and run /compact to summarize the conversation and free space, including with Claude Pro/Max logins.

Expanded sandbox and database support

  • Gensee: provision and clean up managed sandboxes.
  • Kubernetes: run sandboxes on dedicated node pools using tolerations.
  • CockroachDB: use it as Omnigent's application database.

Reliability fixes

  • Pending approvals and requests for user input remain answerable across server and runner restarts.
  • Native Codex sessions resume more reliably, preserving permission overrides and selected reasoning effort.
  • Working indicators more accurately reflect agent activity, and completed answers remain visible when background work resumes.
  • Improved interruption behavior and fixes for archived sessions reappearing.
  • More consistent validation of agent settings and preservation of reviewed tool arguments.

Full changelog

What's Next

Install or upgrade Omnigent:

curl -fsSL https://omnigent.ai/install.sh | sh
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.13.0

Released 2026-09-09 · 3 min read · Omnigent maintainers

Omnigent 0.13.0 is a major release focused on tightening the loop between your agents, your code, and the infrastructure they run on — from watching a branch's pull request come together live inside the workspace to running every session in its own self-reclaiming sandbox. A new GitHub panel puts the PR, its checks, and a full diff right beside the agent, Canvas graduates into a built-in per-project board of live session cards, and a wave of managed-sandbox providers, faster session switching, and new harnesses round out the release.

1. GitHub PR panel in the session workspace

A new GitHub panel in the session workspace rail shows the branch's pull request without leaving Omnigent — the summary, comments, CI checks, and a stacked diff with a file-tree navigator, all refreshing live as the agent pushes. You watch the PR take shape in the same window where the work is happening.

To use it, start a New Chat from a repository with an open pull request, then open the panel and switch between the split Summary and Changes tabs to move from the overview to the file-by-file diff. In managed sandboxes with GitHub Connect configured, private clones and in-session git and gh authenticate as your connected account, so pushes and PR actions run as you.

2. Canvas as a built-in page

Canvas page organizing live Omnigent sessions into draggable project cards

Canvas is now a built-in page rather than a separate extension: a per-project board of draggable session cards, each showing live status, its worktree branch, and a link to its PR. It gives you a spatial, at-a-glance view of everything in flight on a project.

From the board you can open a session's transcript or start a brand-new session in place, so Canvas becomes the launch point for your work rather than just a status display. Enable the built-in page with OMNIGENT_FEATURES=canvas.

3. New managed-sandbox providers

Omnigent gains two new ways to run managed sandboxes. You can run each host in a local libkrun microVM by setting sandbox.provider: microsandbox, which gives you sub-second boots and in-place resume, or run hosts as self-reclaiming Kubernetes agent-sandbox resources that stay alive while an agent is working, suspend when idle, and resume later with their workspace intact.

Both paths are built to avoid waste: sandboxes that remain offline can be reaped automatically, so idle compute doesn't linger.

Learn more in the Cloud Sandbox Host.

4. Instant session switching

Sessions now feel instant. New conversations open immediately while the server catches up in the background, and long transcripts virtualize so switching between them stays fast even when history is deep.

The sidebar keeps up too: rows label themselves with your first prompt and highlight the moment you click them, and new sessions can be auto-named for you — a behavior you can toggle in Settings.

Learn more in the Session management.

5. More harnesses and enterprise CLIs

Omnigent adds more ways to bring your preferred agents along. Jcode joins as a first-class ACP harness, and the EXTRA_HARNESS_CLIS build-arg bakes extra harness CLIs — goose, jcode, cursor, kimi, and more — into the host image, so you can extend the image without forking the Dockerfile.

Enterprises get two more building blocks: an opt-in OAuth 2.0 client-credentials grant, and a HashiCorp Vault Transit backend for the credential store.

Learn more in the Harnesses supported via ACP.

Before upgrading

  • Managed terminals now require tmux 3.3 or newer. Upgrade tmux before launching a managed terminal.
  • The standalone omnigent-canvas extension has been removed. Enable the built-in Canvas page with OMNIGENT_FEATURES=canvas instead.
  • omnigent update is deprecated. Use omnigent upgrade (or omni upgrade) instead.

Full Changelog: https://github.com/omnigent-ai/omnigent/blob/main/CHANGELOG.md

What's Next

Upgrade an existing Omnigent installation:

omni upgrade

Or install Omnigent for the first time:

curl -fsSL https://omnigent.ai/install.sh | sh
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.12.0

Released 2026-09-01 · 3 min read · Omnigent maintainers

Omnigent 0.12.0 is a major release focused on meeting your existing tools and workflows where they already live, from pulling your current CLI conversations into the web UI to running your host as an always-on background service. Projects now shape every new session with their own agent, workspace, and git defaults; the mobile and wide-screen UI gets a top-to-bottom refresh; and a wave of new harnesses and model controls give you finer say over which model runs and how hard it thinks.

1. Import your existing local CLI sessions

If you already have a trail of conversations in Claude Code, Codex, or another CLI, you no longer have to leave them behind. From the web UI you can pull your recent CLI conversations straight into Omnigent, and each one keeps its original title so you can find it again.

This means the work you've already done comes with you — pick up an earlier session in Omnigent instead of starting from scratch.

Learn more in the Import existing chats.

2. Projects that drive new sessions

Projects now shape the sessions you start inside them. Name a project_id when you create a session and it inherits that project's agent, workspace, and git defaults, so a new session starts already pointed at the right code and configuration.

You can also move an existing session into a project straight from the folder tag in its title. And when a session is started from a project, it now uses the project's configured agent and directory instead of silently swapping to something else.

Learn more in the Projects.

3. Refreshed mobile and wide-screen UI

The interface has been reworked to feel right on every screen size. On mobile you get a ChatGPT-style drawer and full-screen search; on ultra-wide displays, Omnigent now makes better use of all that horizontal space.

You also get more control over how it looks and behaves: export and import your appearance settings, switch to a heavier code font, jump around long messages with a markdown table of contents, and choose whether Enter or ⌘-Enter sends your message.

Learn more in the Appearance settings.

4. More harnesses and finer model control

Omnigent 0.12.0 broadens what you can run and how you run it. Antigravity arrives with the omni agy shortcut and agy-native aliases, while Devin and Grok Build now show up in the New Chat picker. Setup also offers a "Pi — use own login" option.

On the model side, the pi harness takes a reasoning-effort setting that you can even change mid-session with /effort, self-hosted models like Ollama and vLLM support custom per-token pricing, and when you fork a session you can give the fork its own model, effort level, and approval mode.

Learn more in the Models & Credentials.

5. Run your host as a service

Your host can now run as a proper background service. Use omni host enable and omni host disable to install a per-user service on macOS or Linux, so your host is there whenever you need it. Running omnigent host or omnigent start opens the web UI for you automatically.

ACP sub-agents such as Devin now appear as their own child sessions, with their tool calls shown right in the transcript, so you can see exactly what each one is doing.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

August 2026


v0.10.0

Released 2026-08-19 · 3 min read · Omnigent maintainers

Omnigent v0.10.0 is a major release focused on scaling out where and how your agents run, from spreading sandboxes across multiple providers to switching conversations instantly. This release adds first-class multi-provider sandboxing with a new Blaxel backend and self-restarting Kubernetes runners, promotes Devin to a built-in harness alongside easier Copilot and ACP-agent setup, introduces a Usage page for tracking cost and spend, and makes session management — moving, forking, and bulk-cleaning sessions — something you can drive entirely from the web UI.

1. Multiple sandbox providers, Blaxel, and self-healing Kubernetes runners

Blaxel sandbox provider panels showing session configuration and sandbox selection

You can now run several sandbox providers side by side. The new sandbox.providers configuration lets you register more than one backend and expose a picker option for each, so different sessions can land on different infrastructure without reconfiguring the server. This release also adds a new Blaxel provider to the mix.

On Kubernetes, runners now launch as Jobs, which means a crashed runner restarts automatically instead of leaving the session stranded. To get a cluster up quickly, there's an ArgoCD quick-start overlay you can deploy from.

Learn more in the Cloud Sandbox Host.

2. Devin as a built-in harness, plus easier ACP and Copilot setup

Devin is now a built-in harness, so you can pick it directly rather than wiring it up by hand. Configured ACP agents — Devin, Grok Build, and others — show up automatically in omni setup and in the New Chat picker, making them selectable the moment they're configured.

The Copilot harness now authenticates using your existing gh auth login session, including GitHub Enterprise hosts, so there's no separate credential dance to get it working.

Learn more in the Configuration.

3. Usage page for cost and spend tracking

Usage page showing session costs, daily spend timeline, and breakdowns by harness and model

A new Usage page gives you visibility into what your sessions cost. It tracks session costs and daily spend, and breaks spending down by harness and by model, so you can see where your budget is going at a glance.

For deployments, you can gate features — including the Usage page itself and web-driven harness setup — behind the OMNIGENT_FEATURES setting, letting you control which capabilities are exposed to your users.

4. Manage sessions from the web UI

Session management is now a full web-UI workflow. You can move a running session to another machine, fork a sub-agent up into its own top-level session, and leave a session someone has shared with you — all without dropping to the terminal.

When it's time to clean up, you can bulk-move or bulk-delete sessions, with optional worktree-branch cleanup so leftover branches don't pile up behind you.

Learn more in the Session management.

5. Instant conversation and terminal switching

Switching between conversations and terminals is now instant. Background conversation streams stay open instead of tearing down and reconnecting, so jumping back into a session is immediate.

Web terminals now attach over loopback when the runner is local, which cuts keystroke echo from around 250 ms down to under 10 ms — typing in a local session feels native again.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.9.0

Released 2026-08-11 · 3 min read · Omnigent maintainers

Omnigent 0.9.0 is a major release focused on putting the right model behind every task and polishing the surface you work on all day, from automatic model-and-harness selection to a refreshed web UI. It brings smart routing that sends each task and its subagents to the best model and harness, a redesigned interface built around a Zinc palette and clearer session controls, deeper control over sandboxes and deployments, a first-class Grok Build harness alongside a set of ship-ready example agents, and new Nimble web builtins for pulling structured data straight off the web.

1. Smart Routing

Smart Routing sending a task and its subagents to the best model and harness

Choosing the right model for a task — and for every subagent that task spawns — is a decision you shouldn't have to make by hand on every run. Smart Routing makes it automatic: each task and its subagents are routed to the best model and harness for the job.

On Databricks, routing is powered by AI Gateway smart routing. In open source, smart routing uses an LLM classifier to pick the best model. Either way, you turn it on once and let Omnigent match work to the model that fits it.

Learn more in the Smart Routing docs.

2. Refreshed web UI

The web UI has been redesigned for clarity: a Zinc palette, tightened typography, flush rails, and unified menus and shadows give the whole interface a calmer, more consistent feel.

Alongside the visual refresh, session management gets more practical. A session filter menu lets you narrow to All, My, Shared, or Archived sessions, the harness picker is now organized by support tier, and settled turns fold away behind a compact "Worked for Xs" row so long conversations stay readable.

Learn more in the Web UI docs.

3. More sandbox and deployment control

This release gives you finer control over where and how agents run. Set sandbox.type: auto to pick the platform default automatically, and size Boxlite disks with sandbox.boxlite.disk_size_gb when a workload needs more room.

For team deployments, you can target per-agent Kubernetes runner Pods by label, set a project default base branch for new worktree sessions, and authenticate headless with omnigent run --profile against a deployed Databricks app.

4. New harnesses and example agents

Grok Build (xAI) joins as a first-class ACP harness, so you can drive Omnigent with xAI's coding agent the same way you would any other supported harness.

The release also ships a set of ready-to-run example agents: a deep-research agent, a repro-agent that reproduces a bug live and authors an end-to-end test for it, and a resolve-agent that fixes the bug and proves the fix. They're a practical starting point for building your own agents around real workflows.

Learn more in the Grok Build docs.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.8.0

Released 2026-08-03 · 3 min read · Omnigent maintainers

Omnigent 0.8.0 is a major release focused on making the platform smarter and more collaborative, from how you pick a model to how you bring in agents. Model choices now come live from your active providers and installed CLIs, the web workspace has been reworked into an editor-style experience, and new guardrail policies catch agents stuck in loops.

1. Live model discovery

Model lists used to be baked into each release, which meant they drifted out of date the moment a provider shipped something new. Now the choices come straight from your active provider catalog and the CLIs you actually have installed — Kiro, Cursor, and Pi — so the models you see are the models you can run.

To keep things stable when an upstream catalog hiccups, Omnigent validates and falls back to a last-known-good catalog, so a provider outage never leaves you without options. You simply pick from the current, live list when you start or switch a session.

2. Reworked web workspace and sidebar

The web workspace now behaves like a real editor. Files and shells open as tabs, with shells docked in the rail and a full-screen toggle when you want room to work. Markdown previews render Mermaid diagrams inline, and the subagent graph is clickable and zoomable so you can trace what your agents are doing.

3. More agents and sign-ins

Omnigent 0.8.0 widens the set of agents you can bring in and how you authenticate them. You can sign in to Antigravity with Google OAuth through agy, and add agy as a Polly sub-agent. Existing OpenClaw and acpx coding agents drop into the ACP picker with omnigent run --from-openclaw, and you can launch Claude and Codex children directly in goal mode.

4. New guardrail policies

Two new policies watch for agents that get stuck. detect_loop and detect_thrashing catch an agent retrying or failing in a loop and prompt you to step in before it burns time and tokens going nowhere.

The GitHub policy also gets safer by default: destructive deletes are now blocked unless you explicitly opt in with allow_destructive: true.

5. Sharper CLI

The command line gets a round of polish. omni upgrade now preserves your installed extras and accepts --extra, --target-version, and --dry-run so you can see exactly what an upgrade will do first. omnigent --help groups and colorizes harness commands for easier scanning, and omnigent diagnose prints a secret-free snapshot of your environment when you need to troubleshoot.

Nightly prerelease builds are now cut automatically, so you can ride the latest with omni upgrade --nightly.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

July 2026


v0.7.0

Released 2026-07-27 · 3 min read · Omnigent maintainers

Omnigent 0.7.0 is a major release focused on putting your agents to work on your own terms, from scheduling recurring tasks that run without you to letting Omnigent pick the right harness and model for the job. This release brings first-class Automations and a dedicated /tasks page, real Project entities that organize your sessions and pre-fill their defaults, hands-free voice dictation in the composer, and smarter routing that chooses both harness and model straight from your task.

1. Automations (Scheduled Tasks)

Some work should just happen on a cadence — a morning digest, a nightly cleanup, a weekly report — without you kicking it off by hand every time. Automations let you set an agent task to run on a recurring schedule and then get out of the way.

A new /tasks page lets you create, edit, and run recurring agent tasks, complete with model and reasoning-effort selectors and a "Run now" action for when you don't want to wait for the next firing. You get live relative next-run times so you always know what's coming up, plus terminal run tracking with full history available at GET /v1/scheduled-tasks/{id}/runs. For chat-only work, tasks no longer require a workspace or a pinned host, so you can automate a conversation as easily as a code job.

Learn more in the Scheduled Tasks.

2. First-class Projects

Projects keep related work grouped instead of scattered across a flat session list. You can create, rename, and delete them right in the sidebar and file your sessions into the project they belong to.

Each project can carry its own default session settings — host, working directory, agent, and model — which pre-fill the new-session composer so you're not re-selecting the same options every time you start work in a familiar context.

Learn more in the Projects.

3. Voice dictation in the composer

Sometimes it's faster to talk than to type. Optional server-side transcription — installed with omnigent[dictation] — lets you dictate straight into the composer, with live streaming partials so you can watch your words appear as you speak.

It works in Electron, Firefox, and Chromium, and your audio never leaves your server. Toggle it from anywhere with ⌘⌥V, and if you'd rather not run transcription in-process, the engine can be offloaded to a remote worker.

4. Smarter routing

Choosing the right harness and model for each task is friction you shouldn't have to think about. A new "Auto · smart routing" harness option lets the router pick both the harness and the model based on your task itself.

Smart routing now activates automatically from your llm:/routing: config — there's no OMNIGENT_SMART_ROUTING env var to set anymore. And when you want to steer things yourself, a composer gear modal lets you tune the model, reasoning effort, and routing mid-chat without leaving the conversation.

Learn more in the Harnesses.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.6.0

Released 2026-07-21 · 3 min read · Omnigent maintainers

Omnigent 0.6.0 is a major release focused on meeting you wherever you work, from bringing your existing chats in and reading files richly to driving sessions from Slack and a desktop app on every platform. It lands a guided theme editor for making the UI your own, first-class Slack control complete with inline approvals, and native desktop apps that now run on Windows and Linux alongside macOS.

1. Richer file viewing

Reading files inside Omnigent now covers far more than plain source. You get inline PDF preview with review comments, find-in-file across the editor, and rendered previews for markdown and notebooks — so you can review what the agent produced without leaving the session.

The diff viewer adds a "Wrap lines" toggle for long lines, and the file panel stays browsable even when the runner is offline, as long as the host is still connected, so you are never locked out of your files mid-session.

Learn more in the Code viewer and diffs.

2. Custom themes

You can now shape Omnigent's look with a guided theme editor. Shared accent, tint, and contrast controls plus a sidebar translucency setting let you tune the whole interface, and there is a new Nord palette to start from — or hit the randomize dice to discover a look you like.

The file editor follows your Omnigent theme too, so your chosen palette carries through from the session view into the code you are reading and editing.

Learn more in the Appearance settings.

3. Bring your existing work in

Starting fresh in a new tool usually means leaving your history behind. Now you can import your Claude Code and Codex chats directly with omni import, bringing up to 50 conversations in at once. Imported and new sessions also get automatic first-turn titles, so your list stays readable without any manual naming.

Learn more in the Import existing chats.

4. Navigation bar in transcript

Long transcripts are now easy to move through. A navigation bar in the session transcript lets you jump around your history with a click, so you can find an earlier turn or result without endless scrolling.

5. Slack integration

Start and manage an Omnigent session from Slack

You can now kick off and drive Omnigent sessions straight from Slack. Beyond starting work, you can approve tool calls and answer the agent's questions inline in the channel, so you can keep a session moving from wherever your team already talks.

Learn more in the Slack.

6. Omnigent desktop app on Windows and Linux

The Omnigent desktop app is no longer macOS-only. Windows and Linux builds are now available, so you can run the native app on your platform of choice. Download the build for your system from the website.

Learn more in the Install.

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
  • Star the project and file issues on GitHub.
  • Join the conversation on our Discord.
  • Browse the docs to go deeper.

v0.5.1

Released 2026-07-10

Bug fixes

  • 🖥️ On older desktop builds without the embedded browser, the Browser tab is now hidden instead of showing a dead tab that does nothing (#2393)
💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our Discord! Thank you for building omnigent with us, keep the bug reports, ideas and contributions coming :)

Full Changelog: https://github.com/omnigent-ai/omnigent/blob/main/CHANGELOG.md


v0.5.0

Released 2026-07-10

Major new features

  • 📱 Omnigent for iOS — now on the App Store — the native iOS app is live on the App Store; Android is coming soon (#2262, #2263, #2282, #2179)
  • 🧩 Generic ACP harness — connect Omnigent to any ACP-compatible agent, bridged to Omnigent's own tools over an MCP relay (#2152)
  • 🔎 Command palette & richer search — a global ⌘/Ctrl+K palette (also wired to the sidebar "Search") jumps across sessions, and session search now shows a highlighted matched-content preview so you can see why a session matched (#1386, #2086, #2162)
  • 🎨 Appearance & customization settings — pick a color theme (Omnigent, Dracula, GitHub, Catppuccin, Gruvbox), a terminal theme, and independent UI and code editor/terminal font size + family (#2225, #2147, #2154, #2135, #2040, #2047)
  • 💬 Message steering & queuing — line up several messages while a turn runs, then edit, reorder, delete, or steer them; queued messages auto-flush on idle, in the background, and across sessions (with attachments) (#2008, #2010, #2019, #2022, #2025, #2029, #2078)
  • ☸️ Kubernetes deployment — a new official omnigent-server-kubernetes image ships the sandbox provider SDK (no custom build), and runner Pods can now schedule on arm64 via node_selector (#2124, #2123)
  • 🌿 Start sessions in git worktrees — pick an existing worktree or generate a fresh branch name right from the new-session composer, see the branch in the sidebar, and delete the worktree + branch on session delete; set a default base branch in Settings › Git (#2088, #2094, #2098, #2267)
  • 🌐 Embedded browser — the Omnigent desktop app now ships a built-in browser pane your agent can drive with framework-owned tools (browser_navigate, browser_click, browser_type, browser_snapshot, browser_screenshot) — it opens a page, reads it, and acts on it without leaving the workspace (#2248)
  • 🖥️ Better web terminal — tmux control-mode (CC) is now the default transport, so the browser owns scrollback and text selection natively in the terminal view (no more fighting tmux for the viewport or mouse), with output coalesced into fewer WebSocket frames for a snappier feel (#1970, #1972)

Bug fixes

  • 🖥️ claude-native reliability — resumed sessions no longer crash on compaction or TaskOutput history, in-pane /model switches no longer stick on "Stop", and mid-turn messages no longer raise a false "terminal did not become ready" error (#1957, #2293, #2082, #2001, #2089)
  • 🧭 Smart routing & compaction — intelligent routing now correctly routes Claude sessions and overrides an orchestrator-specified model when the parent toggle is on, and /compact on a pinned Anthropic model no longer 500s (#2136, #2291, #2043)
  • 🚀 Launch & gateway auth — harness workers now start when Omnigent is launched from a macOS/Linux GUI client (stripped PATH), and managed claude-native sessions against an Anthropic-compatible gateway pass through the model instead of stalling on the API-key menu (#1935, #2371)
  • ✅ Approvals & policies — inbox approvals now resume the gated tool call, and default policies created via the API now take effect on sessions (#2142, #2333)
  • ⏱️ Idle-session stability — messaging a long-idle session no longer risks the new turn being killed mid-flight by the idle reaper (#1834)
💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our Discord! Thank you for building omnigent with us, keep the bug reports, ideas and contributions coming :)

Full Changelog: https://github.com/omnigent-ai/omnigent/blob/main/CHANGELOG.md


v0.4.0

Released 2026-07-03

Install

curl -fsSL https://omnigent.ai/install.sh | sh -s -- --version 0.4.0

0.4.0 turns harnesses into a real plugin platform — bring your own coding agent as an installable package — and matures the whole native-harness fleet with parity, cost, and polish across the board.

Major new features

  • 🤹 Polly multi-agent orchestration: the polly example orchestrator now fans work out across more coding sub-agents — cursor, hermes, and opencode join the roster — so a single run can delegate to the right agent for each task (#1844, #1776)
  • 🔌 Harness plugin SDK: bring your own coding agent — any harness can now ship as an installable Python package (via the omnigent.community.harness entry point), no fork or core changes required. A declarative capability model + a /v1/harnesses catalog let the server and UI discover what each harness supports (#1756, #1847, #1894)
  • 🪢 Native-harness maturity across the fleet:
    • kiro-native reaches full parity: Omnigent tools inside kiro sessions, a launch-time model picker, TUI approvals surfaced as chat cards, working interrupt / Stop, and credit usage tracked as session cost (#1709, #1706, #1715, #1293, #1531, #1699)
    • claude-native renders live tool-call cards in the web chat, shows background-shell status, and takes a pluggable launch command (#1499, #1578, #1476)
    • qwen-native gains Omnigent tools in the TUI and carries conversation history across fork / switch-agent (#1559, #1576)
    • GitHub Copilot reports authoritative AI-credit cost, forwards reasoning effort, emits compaction-complete events, and gates its native tools through policy (#1486, #1503, #1505, #1511)
  • 🧩 VS Code extension (coming very soon): open and drive your running Omnigent server without leaving the editor — landing shortly, not on the Marketplace just yet (#1288, #1855)
  • 🛡️ Better control & elicitation: clicking Decline now cleanly cancels the turn instead of nudging the model to retry, a new intent_gate keeps an agent on its original task, and sub-agents can carry their own cost budgets (#1839, #1777, #1538)
  • 💻 Web & CLI polish: unread/seen state syncs across devices, compaction shows a progress bar instead of a silent pause, a new ! shell passthrough folds command output into your next turn, half-typed drafts survive navigation, the file viewer gains image zoom + inline comments, and the app installs as an offline-capable PWA (#1679, #1304, #1524, #1659, #1775, #116)
  • 🔎 Zero-setup web search: web_search works out of the box with a keyless DuckDuckGo backend; add Tavily for grounded search on any model (#918, #1339)

Bug fixes

  • Connections hold under load — a ws-tunnel keepalive fix ends mid-session disconnects (#1727).
  • Sub-agent results reliably reach the parent session now, instead of getting lost (#1770).
  • pi-native recovers on long sessions — tool calls no longer start failing about an hour in (#1621).
  • Native harnesses survive sandbox restarts — codex/claude-native restore compaction + transcript on resume (#1535).
  • No more zombie processes or runaway terminal panes — orphaned tool/harness processes are reaped and idle panes self-heal (#1812, #1624).
  • Accurate costs — fixed a lost-update race in session usage and stopped double-billing Cursor cache tokens (#1664, #1802).

...and more!


💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our Discord! Thank you for building Omnigent with us, keep the bug reports, ideas and contributions coming :)

Full Changelog: https://github.com/omnigent-ai/omnigent/compare/v0.3.0...v0.4.0

June 2026


v0.3.0

Released 2026-06-27

Major new features

  • 🤖 Seven new agent harnesses: Hermes (SDK + native TUI), GitHub Copilot (SDK), OpenCode, Goose, Qwen Code, Kiro, and Kimi Code; plus Antigravity promoted to a full SDK + native agy CLI harness (#1132, #330, #576, #955, #1020, #899, #521, #892)
  • 🪢 Native-harness parity across the fleet: compaction, cost/token tracking, resume, true fork with history, in-session model switching, and tool-approval / AskQuestion web cards, for cursor, codex, qwen, pi, hermes, goose, and opencode (#1303, #1331, #1271, #1260)
  • 🖥️ Omnigent Desktop: now manages the server + runner automatically (#1437, #1445)
  • 🗂️ Projects workspace: group sessions into Projects and drag between them, plus a Settings surface and per-harness run-mode memory (#1341, #1432, #1110)
  • 📦 More deploy & sandbox targets: host on Databricks Apps + Lakebase Postgres (#956), AWS Bedrock provider (#901), on-demand Kubernetes runner Pod sandbox (#881), and a boxlite managed host (#102)
  • 🪟 Native Windows support (only core features) (#1236)
  • 🕵️ Custom Agent Creation UI (#1098)
  • 🔌 In-app MCP management from Agent Info (#1093), sys_session_share agent-facing session sharing (#985), and web UX polish — shortcuts overlay, pinned-session hotkeys, image lightbox (#833, #967, #1334)

Bug fixes & hardening

  • Authoritative context-window resolution + compaction-failure surfacing + /context meter; compaction ownership moved runner→harness, ending compact-every-message (#1121, #1169, #1082).
  • Native harnesses no longer fail silently — codex/antigravity surface real turn/model/auth errors instead of empty/false success (#1108, #1172).
  • Policy checks fail closed when turn context is missing (#1078).
  • Parallel sub-agents — serialized continuation turn-starts fix the 204 race (#996).
  • claude-native stability — tmux server survives inner-CLI exit (#849). ...and more!

Full Changelog: https://github.com/omnigent-ai/omnigent/compare/v0.2.0...v0.3.0rc1


💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our Discord! Thank you for building Omnigent with us, keep the bug reports, ideas and contributions coming :)


v0.2.0

Released 2026-06-19

Install

curl -fsSL https://omnigent.ai/install.sh | sh -s -- --version 0.2.0

0.2.0 turns omnigent into a multi-vendor agent platform with pluggable agent SDKs, a much wider fleet of sandbox & deploy targets, and hardened security underneath.

Major new features

  • 🤖 More agent harnesses & SDKs
    • run agents on Google Antigravity (Gemini 3 Pro, also Claude/GPT-OSS) (#194)
    • Cursor via a first-party Python SDK and a native cursor-agent (ACP) harness with cost tracking (#203, #551, #635)
    • Native /compact for Codex and Pi login folded into omnigent setup (#285, #207)
  • 📦 More sandboxes & deploy targets
    • new sandbox providers NVIDIA OpenShell, E2B, CoreWeave, and Podman (#227, #565, #302, #401)
    • deploy to Cloudflare Containers (D1 + R2) with an S3 artifact store, plus a UBI9 image for RHEL/OpenShift (#651, #167)
  • ⬆️ omni upgrade: self-upgrade the CLI to the latest release, with an out-of-date notice on startup (#188).
  • 🔒 Secretless sandbox egress: credential_proxy injects bearer/basic auth for allow-listed hosts so secrets never enter the sandbox (#236)
  • 📊 MLflow tracing end-to-end through omnigent run (#638)

Bug fixes

  • omni upgrade is version-aware — upgrades to the right release instead of looping against a stale version (#726).
  • omnigent run exits cleanly on an INPUT-phase policy denial instead of hanging (#599).
  • The REPL no longer crashes when the daemon returns a non-JSON status response (#660).

Full changelog: https://github.com/omnigent-ai/omnigent/compare/v0.1.1...v0.2.0


💜 Thanks to our community

This release was shaped by the people who filed issues, opened PRs, and talked through feature requests with us on our discord! Thank you for building Omnigent with us, keep the bug reports, ideas and contributions coming :)