Gives Claude Code skills, agents, and commands for PostHog analytics, session replay, feature flags, error tracking, and LLM observability. Includes MCP server setup and project access checks.
Claude Code
$ npx -y skills add posthog/posthog --agent claude-code
Codex
$ npx skills add posthog/posthog -a codex
Cursor
$ npx skills add posthog/posthog -a cursor
Gemini CLI
$ npx skills add posthog/posthog -a gemini-cli
GitHub Copilot
$ npx skills add posthog/posthog -a github-copilot
OpenCode
$ npx skills add posthog/posthog -a opencode
Windsurf
$ npx skills add posthog/posthog -a windsurf
Docs - Community - Roadmap - Why PostHog? - Changelog - Bug reports
PostHog ingests and stores your analytics, errors, replays, and business data so you and your agents can query and act on it. It gives you every tool you need to build a successful product, and captures the context agents need to diagnose problems, uncover opportunities, and ship fixes:
Analytics
Session replay
Observability
Ship and iterate
Talk to users
Data
AI and agents
You can steer it all from Slack, web, desktop (PostHog Desktop), or your own editor via the MCP.
What is this, a readme for agents?
The remote MCP server is https://mcp.posthog.com/mcp. It routes to the correct data region (US or EU) when your human logs in. Install it into Claude Code, Cursor, Codex, VS Code, Zed, or PostHog Desktop with:
npx @posthog/wizard mcp add
The docs are indexed for you at posthog.com/llms.txt, the changelog is plain Markdown at posthog.com/changelog.md, and the setup guides for every MCP client are in the docs.
All of this is free to use with a monthly free tier for each product. No card is required, and 97% of users pay $0. Join the 500,000+ teams already shipping with PostHog by signing up for PostHog Cloud US or PostHog Cloud EU.
The fastest and most reliable way to get started with PostHog is signing up for free to PostHog Cloud or PostHog Cloud EU. Your first 1 million events, 5k recordings, 1M flag requests, 100k exceptions, 10GB of logs, and 1500 survey responses are free every month, after which you pay based on usage.
If you want to self-host PostHog, you can deploy a hobby instance in one line on Linux with Docker (recommended 4GB memory):
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/posthog/posthog/HEAD/bin/deploy-hobby)"
Open source deployments should scale to approximately 100k events per month, after which we recommend migrating to a PostHog Cloud.
We do not provide customer support or offer guarantees for open source deployments. See our self-hosting docs, troubleshooting guide, and disclaimer for more info.
Once you've got a PostHog instance, the fastest way to set it up is the setup wizard, which installs and configures PostHog in your app for you:
npx -y @posthog/wizard@latest
You can also install our JavaScript web snippet, one of our SDKs, or use our API. You can also connect the MCP to bring PostHog into Claude Code, Cursor, or any MCP-compatible agent.
We have SDKs and libraries for popular languages and frameworks like:
| Frontend | Mobile | Backend |
|---|---|---|
| JavaScript | React Native | Python |
| Next.js | Android | Node |
| React | iOS | PHP |
| Vue | Flutter | Ruby |
Beyond this, we have docs and guides for Go, .NET/C#, Django, Angular, WordPress, Webflow, and more.
Once you've installed PostHog, see our product docs for more information on how to set up product analytics, web analytics, session replays, feature flags, experiments, error tracking, surveys, data sources, and more.
Our code isn't the only thing that's open source 😳. We also open source our company handbook which details our strategy, ways of working, and processes.
Stars on GitHub
View @posthog’s profilePlugin for PostHog product analytics, feature flags and session replay inside AI coding tools. Adds skills for analyzing experiments, AI costs and offline evaluations, plus an MCP server.
@posthogA Claude Code plugin that saves and shares your coding sessions to GitHub repositories in readable markdown format.
@posthogReads text from scanned pages, photos and PDFs and returns it as structured Markdown or JSON, so you can pull tables, formulas and headers out of a document without retyping them. Covers many languages and works as input for AI tools.
@paddlepaddleGives your AI assistant a memory that persists across sessions, so it remembers your preferences and earlier work in this repository instead of starting fresh. Search, forget, pause and resume memories with simple commands.
@mem0aiGives AI agents a library of ready-made skills for scientific work such as metabolic flux analysis, protein experiment design, time series modeling, and analytical method validation, so research tasks need less hand-built code. It works with any agent that supports the open Agent Skills standard.
@k-dense-aiSearches local markdown notes, docs, and wikis on your device using keywords or natural language. Lets Claude Code find notes, retrieve documents, and answer from indexed markdown.
@tobiInstall it with the command on its page. It includes mcp-servers, dynamic-workflows, subagent-orchestration. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it