惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 三生石上(FineUI控件)
J
Java Code Geeks
Apple Machine Learning Research
Apple Machine Learning Research
Jina AI
Jina AI
博客园_首页
C
Check Point Blog
小众软件
小众软件
博客园 - 叶小钗
Blog — PlanetScale
Blog — PlanetScale
Engineering at Meta
Engineering at Meta
美团技术团队
Martin Fowler
Martin Fowler
Vercel News
Vercel News
D
Docker
罗磊的独立博客
B
Blog RSS Feed
The Cloudflare Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - 聂微东
Last Week in AI
Last Week in AI
T
Tailwind CSS Blog
雷峰网
雷峰网
博客园 - Franky

Mintlify Blog

22 UX improvements to the web editor Introducing the Mintlify Help Center Starter Kit Introducing the collaborative editor built for teams and agents Workflows, rebuilt Is your documentation agent-ready? Mintlify raises $45M Series B led by Andreessen Horowitz and Salesforce Ventures 5 things you didn't know you could do in the Mintlify web editor Docs on autopilot: From zero to self-maintaining with Mintlify The state of agent traffic in documentation (March 2026) How we built a virtual filesystem for our Assistant We Replaced Our Internal Wiki With a Slack Bot. You Should Too. 8 ways teams use Mintlify to keep docs updated automatically Documentation is your AI interface What three years of watching AI in production taught us Bridging two JSX runtimes: How we solved Astro's React children problem AI agents are shipping faster than anyone can document Knowledge management systems for technical teams Workflows: Automate documentation maintenance Mintlify acquires Helicone to redefine AI knowledge infrastructure Why more product managers are switching to Mintlify Auto-generating documentation sites from GitHub repos Your docs, your frontend, our content engine Take control of your documentation system Almost half your docs traffic is AI, time to understand the agent experience @mintlify for better docs, faster Mintlify for Enterprise Real llms.txt examples from leading tech companies (and what they got right) Mintlify + Claude Opus 4.6: Powering AI-native knowledge management Declaring Clankruptcy: An experiment in agent orchestration Analytics for AI and agent traffic
The improved Mintlify CLI
Han Wang · 2026-04-07 · via Mintlify Blog

Until now, the mint CLI has been mostly a local preview tool. You run mint dev, check that your docs look right, and push. That workflow is unchanged, but the CLI can do a lot more now.

Today we're shipping mint analytics, mint login, and a set of new commands that bring the Mintlify dashboard into your terminal. Manage your docs workflow from the CLI to augment it with agent-driven development with tools like Claude Code, Cursor, and Devin.

mint analytics gives you direct access to your documentation analytics from the command line. All the data you'd normally check in the dashboard like page views, search queries, assistant conversations, and user feedback is now available in your terminal.

The commands break down like this:

mint analytics stats                              # views, visitors, searches, feedback, assistant usage
mint analytics search                             # search queries with hit counts and CTR
mint analytics feedback                           # user-submitted feedback
mint analytics conversation list                  # list assistant conversations
mint analytics conversation view <id>             # view a single conversation
mint analytics conversation buckets list          # list grouped conversation categories
mint analytics conversation buckets view <id>     # view conversations in a category

Every subcommand supports --from, --to, and --page flags, so you can slice data by date range, page path, or traffic source. Each outputs structured data you can pipe, filter, and act on. But the real value is what happens when you combine this with a coding agent.

Claude Code can run mint analytics as part of a session, so you can give your agent full context on how users interact with your docs. Instead of switching to the dashboard, copying data, and describing what you see, you can pipe analytics output directly into a prompt.

Some examples of what this looks like in practice:

Find and fix content gaps. Pull your search queries with low click-through rates, hand them to Claude Code, and ask it to identify which pages need better coverage. The agent can read your existing docs, cross-reference the search data, and draft improvements in one pass.

Prioritize what to write next. Feed your assistant conversation categories into Claude Code and ask it to rank documentation gaps by frequency. You get a data-driven content roadmap without manual analysis.

Respond to user feedback. Pipe mint analytics feedback into your agent, and let it triage issues, suggest fixes, and even open PRs against your docs repo.

This is what agent-native documentation tooling looks like. Your agent already knows how to write and edit docs. Now it also knows how your users actually use them.

We've also shipped search and the AI assistant on local previews. Previously, mint dev gave you a visual preview but with search fully disabled, meaning the only way to navigate your local docs was by clicking through the sidebar. That made it difficult to test the actual user experience.

Now when you run mint dev, search works out of the box. The AI assistant is also available on local previews for Pro and Enterprise accounts. You'll need to run mint login first to authenticate, and then your local preview behaves just like what your users see in production.

The new CLI commands for identity management:

mint login     # OAuth authentication via Stytch
mint logout    # end your session
mint status    # check your current session
mint signup    # CLI-based onboarding for new users

mint login is the foundation for the authenticated CLI features. Once you're logged in, you get access to mint analytics, the assistant on local previews, and the other platform features we're building. Your session persists, so you authenticate once and keep working.

This release is the beginning of a larger effort to make the CLI a first-class interface to the Mintlify platform. The long-term vision is parity with the dashboard: deployment management, configuration, team settings, and more, all from the terminal.

We're building for a world where coding agents handle more of the docs workflow end to end. That means the tools need to meet agents where they are, in the terminal, with structured output, behind standard auth.

Update your CLI and log in:

npm i -g mint@latest
mint login
mint analytics stats

Check out the CLI documentation to explore all the new commands.