It hasn't been long since the 0.55 update, but plenty has landed since. Let's go through the highlights as of v0.63.What's agent-shell?agent-shell is a native Emacs mode to interact with AI agents powered by ACP (Agent Client Protocol).Supported agentsThe roster keeps growing. This cycle adds two new agents:Grok Build (xAI), #720 by @eddof13.Oh My Pi (omp), #631 by @tychoish.Additionally:Cursor now runs on the official Cursor CLI (agent acp). Note a recent CLI is required, as the acp subcommand was only added in 2026.Codex now uses @agentclientprotocol/codex-acp.Cline now accepts a default model and session mode via defcustoms (#693 by @nhojb).Goose no longer requires an OpenAI key by default (#711 by @hoyon).Qwen now has explicit support for OpenAI-compatible keys.Custom markdown renderersThe new markdown renderer introduced in 0.55 is now extensible. Third-party packages can claim and render specific markdown constructs (source blocks, inline code ranges, and more) through a set of now-public helpers.Thanks to Andrea Alberti for driving the first integration in agent-shell-math-renderer, which renders LaTeX math equations as SVGs.agent-shell facesIf you've wanted more theming control over agent-shell buffers, this is now possible via agent-shell-faces.el. Additionally, check out agent-shell-markdown.el for Markdown theming.Less chatter, more groupingIf your agent session requires lots of tool use (fairly typical), you may notice that shell output is fairly verbose or chatty. This can be quite distracting, so from now on, tool usage as well as thinking are grouped together under an "Activity" section (collapsed by default). If you're a fan of the chatty output, not to worry. Use agent-shell-activity-group-expand-by-default to expand the lot by default.The new "Activity" section has customisable headers (via agent-shell-activity-group-header-label-function). You now have three ways of rendering the activity header:DescriptiveCollapsedExpanded(setq agent-shell-activity-group-header-label-function #'agent-shell-activity-group-descriptive-label)CountCollapsedExpanded(setq agent-shell-activity-group-header-label-function #'agent-shell-activity-group-count-label)TallyCollapsedExpanded(setq agent-shell-activity-group-header-label-function #'agent-shell-activity-group-tally-label)Inline image and rich content renderingagent-shell can now render agent-supplied image content inline, whether base64-encoded, a remote URL, or a resource_link=/=resource content block (#676 by @melito). Audio and other binary resources now render as links you can open externally.Per-agent MCP serversYou can now attach MCP servers to a specific agent through its config's :mcp-servers entry, rather than sharing one global list across every agent, as requested in #593.Diff improvementsSection titles now summarize lines added and removed.In addition, pressing RET in a diff buffer jumps to the file location where the change would apply, while multi-diff permission requests are now supported.Improved out-of-turn handlingSome agents emit notifications outside of the usual prompt session request/response turn. Historically, these have been dropped by agent-shell. These out-of-turn notifications should now render as expected. Please file a bug if you continue to run into issues.New copy commandsA few new commands for grabbing hidden content out of the shell buffer:M-x agent-shell-copy-as-markdown copies buffer text as markdown.M-x agent-shell-copy-source-block-at-point copies the source block at point.M-x agent-shell-copy-link-url-at-point copies the URL of the link at point.Viewport tweaksThe viewport picked up a few refinements:agent-shell-viewport-dismiss-on-send dismisses the viewport once you send.Submitting prompts via C-u C-c C-c now enables you to continue queuing additional requests.History navigation now preserves your in-progress prompt.Session choicesThe new agent-shell-session-choices-function lets you customize what options are presented when starting a new shell. This is useful if you'd like to hide some of these options:Agent-specific notification adaptersA new notification-adapter mechanism enables agent-specific logic to preprocess notifications before handing back to agent-agnostic handling, starting with a Cursor notification adapter (#702 by @aburtsev).Narrow to blockM-x agent-shell-narrow-to-block narrows the buffer to the most recent N blocks (defaulting to 1), handy for focusing on the latest exchange (#672 by @arthurgleckler).Keeping the system awake while busyTo keep a long agent turn from being cut short by idle sleep, agent-shell now keeps the system awake while an agent is busy, releasing it as soon as the turn finishes (the display may still blank). It won't override a hard sleep such as closing a laptop lid. This needs the system-sleep library (Emacs 31.1+) and can be disabled via agent-shell-inhibit-system-sleep. Thanks to @shipmints for proposing the idea.Artist supportM-x agent-shell-artist-insert-text-drawing lets you sketch simple text drawings to drop into a prompt. Check out Bending Emacs episode 14 for a demo, crafting iOS UI.New third-party packagesThe agent-shell package family keeps expanding. Recent additions:agent-shell-math-renderer: Render LaTeX math equations as SVGs in agent-shell.agent-shell-dashboard: A landing page for agent-shell.agent-shell-links.el: Bookmarks and Org links for agent-shell sessions.agent-shell-desktop: Desktop save mode integration, resuming shells by folder, config, and session id.Maintenance and housekeepingKeeping up with the project requires daily work. Luckily, I'm getting a bit better at time management since my new 24-hour job, so I've been catching up on general project maintenance, delivering bugfixes and feature requests, merging pull requests, and general bookkeeping.At its most backed-up period, in mid-May, agent-shell's open issues peaked at 75 while pending PRs peaked at 29.As of today, we are down to 13 open issues and 4 open PRs.Side note: this chart was generated using the /github-activity skill shared in my emacs-skills repo.agent-shell needs your supportVendor-neutral tooling matters, and there are a couple of ways to help keep agent-shell going. Some cost money, others just a click. All are appreciated ;)Sponsorships for agent-shell longevityagent-shell is just me, an indie dev, while the tools it competes with have well-funded teams behind them. If this project is useful to you, please consider sponsoring the project. And if your employer benefits from your agent-shell use, nudge them to chip in too, they can typically contribute at a scale individuals can't.GitHub stars for Anthropic creditAnthropic offers 6 months of free Claude Max 20x for qualifying open-source projects with at least 5,000+ GitHub stars. Starring agent-shell costs nothing and can save me some money, so if you don't mind a couple of clicks, the project can really use another GitHub star.Pull requestsThank you to all contributors for these improvements!#629: Write .agent-shell/ to .git/info/exclude instead of .gitignore (@phairoh)#631: Add implementation/support for oh-my-pi (omp) (@tychoish)#632: Render tool call parameters for non-standard tools like MCP calls (@martenlienen)#633: Add GitHub Actions workflow for ERT tests (@phairoh)#634: Update art generated by agent-shell-hermes--ascii-art (@TamsynUlthara)#639: Preserve window position when restarting (@Gleek)#647: Adjust region line counting when ending at the beginning of a line (@bcc32)#648: Don't italicize intraword underscores (@liaowang11)#651: Post test results on fork PRs (@phairoh)#652: Fix file paths in README for model registration (@vellvisher)#653: Add a reference to agent-shell-desktop.el (@timfel)#656: Fix previous-item skipping the current fragment's heading (@liaowang11)#658: Fix viewport previous-page navigation and stale position label (@liaowang11)#659: Use native ERT JUnit reporting in CI (@phairoh)#661: Don't delete temp dir on agent-shell-restart (@arthurgleckler)#664: Fix transcript section heading glued to interrupted agent message (@liaowang11)#665: Don't trigger completion on path separators in file paths (@liaowang11)#666: Preserve viewport edit draft when queued request executes (@liaowang11)#667: Fix markdown rendering for non-streamed bodies (@arthurgleckler)#672: Add agent-shell-narrow-to-block (@arthurgleckler)#676: Render agent image content blocks inline (@melito)#686: Fix command to pull Qwen2.5 model in README (@jcubic)#687: Record session ID and model in transcript header (@alberti42)#693: Fixes for cline agent (@nhojb)#695: Fix unexpected resize of the window header (@jcubic)#696: Strip source-buffer properties from grabbed region context (@liaowang11)#697: Fix agent-shell-send-dwim double-inserting context with prefix arg (@liaowang11)#698: Fix mouse-copy inside formatted text (@jcubic)#702: Add cursor toolcall output adapter (@aburtsev)#707: Add hermes to default agent configs (@eliferrous)#709: Prevent programmatic fragments ending up in undo history (@martinbaillie)#711: Update goose to not require OpenAI key by default (@hoyon)#713: Align embedded-image rendering with link rendering (@alberti42)#715: Fix table column wrapping for CJK text (@ktakahashi74)#716: Fix resuming copilot session (@gnufied)#717: Make the markdown render context available via a public function (@alberti42)#720: Add first-class Grok Build (xAI) ACP support (@eddof13)#721: Fix hidden streamed Markdown headings (@regadas)#727: Fetches the proper Pi logo (@JanJoar)Make it sustainable, sponsor the effortLiking agent-shell? Would like to see it evolve? Consider sponsoring the effort.