AI is a real force multiplier for software development. It's also the ideal companion for solving technical problems fast. But all that knowledge — we keep it to ourselves. Or rather, we lose it.
Question → answer → problem solved — and the conversation sinks into the chat history, gone.
Then someone else hits the exact same wall. Same cycle: question → answer → problem solved — and the conversation sinks into the chat history, gone.
That's the problem. Not that AI can't solve the same issue twice — it's that a working solution already exists somewhere: someone already investigated, tested, found the fix, and had a conversation detailed enough to explain it properly.
Why should that knowledge evaporate the moment the session ends? Why keep asking the same question over and over — burning electricity, water, and time that's already been spent — instead of recycling that raw material?
Shared Knowledge is an MCP server that turns a solution from an AI conversation into a proposed Markdown article, then into a GitHub Pull Request submitted for human review. Once merged, the contribution is published to a documentation site and gets an audio version generated with ElevenLabs.
The project turns a solved problem into a reusable piece of community knowledge — but only when the user makes the explicit decision to share it.
The conversation itself stays strictly private. The MCP server extracts only the relevant solution, structures it as a standalone English Markdown article, validates it, and opens a Pull Request on GitHub.
Nothing gets published automatically. A human reviews the contribution and decides whether it belongs in the shared knowledge base. Only once the PR is merged does the article land on the public documentation site, which in turn kicks off its audio version.
AI conversation → explicit sharing → MCP → Markdown → Pull Request → human review → merge → docs + audio
The one boundary that matters is human review. The MCP can structure knowledge and prepare a contribution — it can't decide, on anyone's behalf, what deserves to become public knowledge.
The public documentation site is live: {%embed https://pcescato.github.io/shared-knowledge/ %}
It currently hosts four published articles, each with a generated audio version.
To prove the system actually works across different clients — no shortcuts, nothing hard-coded — I tested publishknowledge through two very different paths.
The first contribution published through Shared Knowledge went out as a real Pull Request: Optional dependency crashes the import chain when the import itself isn't optional.
That PR walks through the whole flow end to end: a real technical problem solved with an AI assistant (an optional dependency in pyproject.toml that crashed the import chain); an explicit turn into a structured Markdown article (sections, metadata, tags); automatic validation by the MCP server, which opens the PR; an automated review from GitHub Copilot, flagging YAML formatting and heading issues; fixes applied, then a merge into main; and, after the merge, an ElevenLabs audio version generated and published to the docs site.
That first PR is also a concrete act of generosity: someone took the time to turn their fix into a resource every future developer hitting the same wall can reuse.
Next, I used a real AI client — GitHub Copilot Chat in Agent mode, running inside a Codespace.