agent-shell 0.63 updates

Agent-shell 0.63, an Emacs mode for interacting with AI agents via the Agent Client Protocol (ACP), adds two new agents, a markdown renderer extensible by third-party packages, inline image rendering, per-agent MCP server configuration, and an "Activity" section that groups tool usage and thinking output. The update also introduces new commands for copying hidden content, viewport refinements, and a customizable session-choices function.

It hasn't been long since the 0.55 update https://xenodium.com/agent-shell-0-55-updates , but plenty has landed since. Let's go through the highlights as of v0.63. agent-shell ? agent-shell https://github.com/xenodium/agent-shell is a native Emacs https://www.gnu.org/software/emacs/ mode to interact with AI agents powered by ACP Agent Client Protocol https://agentclientprotocol.com/ . The roster keeps growing. This cycle adds two new agents: Additionally: agent acp . Note a recent CLI is required, as the acp subcommand was only added in 2026.The 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 https://github.com/alberti42 for driving the first integration in agent-shell-math-renderer https://github.com/alberti42/agent-shell-math-renderer , which renders LaTeX math equations as SVGs. If 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. If 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: Collapsed Expanded setq agent-shell-activity-group-header-label-function 'agent-shell-activity-group-descriptive-label Collapsed Expanded setq agent-shell-activity-group-header-label-function 'agent-shell-activity-group-count-label Collapsed Expanded setq agent-shell-activity-group-header-label-function 'agent-shell-activity-group-tally-label agent-shell can now render agent-supplied image content inline, whether base64-encoded, a remote URL, or a resource link=/=resource content block 676 https://github.com/xenodium/agent-shell/pull/676 by @melito https://github.com/melito . Audio and other binary resources now render as links you can open externally. You 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 https://github.com/xenodium/agent-shell/issues/593 . Section 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. Some 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 https://github.com/xenodium/agent-shell/issues if you continue to run into issues. A 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.The viewport picked up a few refinements: agent-shell-viewport-dismiss-on-send dismisses the viewport once you send. C-u C-c C-c now enables you to continue queuing additional requests.The 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: A 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 https://github.com/xenodium/agent-shell/pull/702 by @aburtsev https://github.com/aburtsev . M-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 https://github.com/xenodium/agent-shell/pull/672 by @arthurgleckler https://github.com/arthurgleckler . To 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 https://github.com/shipmints for proposing the idea https://github.com/xenodium/agent-shell/issues/644 . M-x agent-shell-artist-insert-text-drawing lets you sketch simple text drawings to drop into a prompt. Check out Bending Emacs episode 14 https://www.youtube.com/watch?v=7fdHeUoRRgg for a demo, crafting iOS UI. The agent-shell package family keeps expanding. Recent additions: agent-shell . agent-shell . agent-shell sessions.Keeping up with the project requires daily work. Luckily, I'm getting a bit better at time management since my new 24-hour job https://xenodium.com/and-then-there-were-three , 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 https://github.com/xenodium/emacs-skills repo. Vendor-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 ; agent-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 https://github.com/sponsors/xenodium 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. Anthropic offers 6 months of free Claude Max 20x https://claude.com/contact-sales/claude-for-oss for qualifying open-source projects with at least 5,000+ GitHub stars. Starring agent-shell https://github.com/xenodium/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 https://github.com/xenodium/agent-shell/ . Thank you to all contributors for these improvements .agent-shell/ to .git/info/exclude instead of .gitignore agent-shell-hermes--ascii-art Liking agent-shell ? Would like to see it evolve? Consider sponsoring https://github.com/sponsors/xenodium the effort.