Is the era of paying $200/month for AI documentation search over?

Hey makers and developers!

Over the past year, nearly every documentation platform rolled out an AI chatbot. But almost all of them followed the exact same monetisation playbook: high monthly subscriptions ($100 to $500/mo), query caps, and vendor lock-in on your own search index.

With docmd, we took the opposite approach: what if the AI assistant was simply a native, free feature of the open-source documentation generator itself?

With docmd AI Assistant, there are no monthly subscriptions, no middleman tracking, and no per-query markups. You get:

- Bring-Your-Own-Key (BYOK): Plug in your own API key for OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Groq, or run completely offline with local Ollama.

- Native In-Doc Chat: Instant chat overlay with grounded RAG answers, direct source links, and starter prompt suggestions.

- Dual Human & Agent Access: The same engine auto-generates `llms.txt` manifests and runs a native stdio MCP server for Cursor and Claude Desktop.

- Lightweight: The entire browser payload is just ~18 KB (14 times lighter than Docusaurus).

Everything is 100% free and open-source (MIT).

I would love to hear how other developers, founders, and technical writers view this:

1. Have you integrated an AI assistant into your product docs yet?

2. What held you back most: cost, data privacy, or hallucination concerns?

3. Would you rather bring your own API key for pennies or pay a monthly flat fee for a managed SaaS widget?

Looking forward to hearing your thoughts and experiences!