Teaching your coding agent to design: two new skills, plus a self-hosted Intercom
Two of this week's tools install with a single npx command and then live inside Claude Code. One turns a text prompt into a Lottie animation. The other lays out a resume or a slide deck that doesn't look like a Canva template. You're not running an app, you're handing your coding agent a new trick and letting it do design work it had no business doing a year ago. That document designer is named Kami, which also happens to be my three-year-old daughter's name, so I'll be straight with you: it was making this list either way. It earned the spot on its own, but I wasn't going to pretend to be neutral about it. Chatwoot is the featured pick and the most production-ready of the bunch: a self-hosted support inbox that covers the core of what Intercom and Zendesk bill you per agent for. The honest catch is operational. You're standing up Rails, Postgres, Redis, and Sidekiq, so it fits if you've got the ops muscle and want off the per-seat treadmill, not if you want something running by lunch. openhuman is the long shot. A local-first personal assistant that keeps your data as plain markdown on your own machine and connects to a hundred-plus services. It's early beta and says so plainly. Worth a look if you like poking at ambitious privacy-first software, worth skipping if you need it to just work.
Open source live-chat and support desk
The Lens
Chatwoot puts every customer conversation in one shared inbox: website live chat, email, WhatsApp, Facebook, Instagram, Telegram, SMS and more, with a help center, canned responses, automation and reports on top. It's the open source answer to Intercom and Zendesk, and the Community Edition is free to self-host under MIT. Running it means a Rails app, a Sidekiq worker, Postgres and Redis, and Chatwoot recommends at least 4GB of RAM and 2 CPU cores for production. Docker, Kubernetes and Heroku guides exist. Each channel still needs its own provider setup, so budget time for WhatsApp and Meta. Free doesn't mean everything. Custom branding, roles and permissions, agent capacity, SSO, SLA policies and the Captain AI agent live in a proprietary enterprise folder that needs a paid self-hosted plan: Premium Support at $19/agent/month or Enterprise Edition at $99. Chatwoot Cloud has a free Hacker plan (2 agents, 500 conversations, live chat only), then $19, $39 and $99 per agent per month. Solo: free. Small teams: free Community Edition or cloud Startups. Larger teams: budget for Enterprise. The catch: patch promptly. The conversation and contact filter API shipped SQL injection bugs in both 2025 and 2026, both fixed.
Open-source skill and harness for generating production ready Lottie animations with codex/claude code
The Lens
This turns "make me a loading spinner animation" into actual Lottie code through your AI coding agent. Lottie is the format apps use for lightweight vector animations, and creating them normally means After Effects and a plugin. diffusionstudio/lottie installs as a skill for agents like Claude Code, then converts an SVG or a plain-text description into working animation code you can drop into web, React Native, iOS, Android, or Flutter. Setup is one command, npx skills add diffusionstudio/lottie, and you're generating animations by prompting. There's nothing to host and no account. Because it produces standard Lottie JSON, the output plugs into the same players and tooling you'd already use. The whole thing is MIT-licensed and free. Developers who need simple animations but don't have a motion designer, or don't want to learn After Effects, are the target. It won't replace a real animator for complex, hand-crafted motion work. For spinners, icon transitions, and straightforward UI animation, it's a fast path from idea to code without leaving your editor. The catch: it leans on your AI agent, so the quality of what you get tracks the quality of your prompt and your model. Intricate animation is still beyond what a text prompt produces cleanly, this shines on the simple-to-moderate stuff. Think of it as a head start, not a finished motion-design studio.
👩🚒 Good content deserves good paper.
The Lens
Kami is a design system for professional documents. You feed it content through Claude Code or another AI agent, and it outputs HTML in a warm-parchment, ink-blue style. It now ships nine template types: one-pagers, long documents, formal letters, portfolios, resumes, slides, equity reports, changelogs, and landing pages. MIT-licensed. Installation is loading one skill into your agent of choice, available for Claude Code, Claude Desktop, Codex, and generic agent frameworks. No app to run. The system enforces typography and spacing rules so output stays consistent whether you are writing a one-page memo or a long report, and it now includes built-in SVG diagram types plus Mermaid support for sequence, class, and ER diagrams. HTML output means you print directly or export to PDF. English, Chinese, and Korean are all supported. Writers and analysts who need polished docs without opening InDesign get a sensible default. Job seekers get resume templates that do not look like every other Canva export. Solo creators get a style system they can extend. No paid tier. The catch: the Chinese serif font (TsangerJinKai02) is free for personal use only. Commercial use of that font requires licensing from tsanger.cn. Documents in English or Korean, and Chinese docs using a different font, are fully unrestricted.
Your Personal AI super intelligence. Private, Simple and extremely powerful.
The Lens
OpenHuman is a desktop AI agent that connects to more than a hundred services, pulls your data in on a schedule, and builds a memory it can act on, with web search, voice, code execution and a talking desktop mascot built in. It's repositioning as an agent harness with a Rust core. The app is GPL-3.0; the managed services behind it are not. Install is native: Homebrew cask, .dmg, .msi, .deb or AppImage, no Docker. By default you sign in and use the TinyHumans managed route for models, search and integrations. Bring-your-own keys for 26 providers and local models through Ollama, LM Studio or MLX are options, and a local-only privacy mode keeps inference on the device. Integrations run through TinyHumans' backend via Composio by default. It was never fully free. TinyHumans sells credit plans: Basic $20 a month or $200 a year with $21 of credits, Pro $200 a month or $2,000 a year with $210, and pay-as-you-go top-ups from $5, all non-refundable. Solo users running local models can avoid paying. Everyone on the default managed route is buying credits. The catch: the local-memory pitch is going away. The development branch replaces the on-disk Markdown memory and Obsidian vault with CortexDB, hosted by TinyHumans or self-hosted by you; with neither, memory is off. It's also an early beta with hundreds of open issues.
Get the next issue in your inbox
Free. No spam. Unsubscribe anytime.