Show HN: I got tired of syncing Claude/Gemini/AGENTS.md and .cursorrules

Post by wolfejam » Fri, Feb 27, 2026, 5:39 PM UTC

  I kept forgetting to update one, then wondering why Cursor was hallucinating my project structure while Claude had it right.

  So I built an MCP server that reads a single YAML file (project.faf) and generates all
   four formats. 7 bundled parsers handle the differences between them. You edit one file, and bi-sync keeps everything current.

  It's an MCP server, so Claude Desktop can use it directly. 61 tools, 351 tests, no CLI dependency.

  Try it: npx claude-faf-mcp

  Source: https://github.com/Wolfe-Jam/claude-faf-mcp

  The .faf format itself is IANA-registered (application/vnd.faf+yaml).

  Curious if others are dealing with this multi-AI config problem, or if there's a simpler approach I'm not seeing.

Post by wolfejam » Fri, Feb 27, 2026, 6:47 PM UTC

verdverm wrote: post #2

use git with a repo, like so many do for their dotfiles if your agent cannot be populated from there as well, you are using the wrong framework / setup

Post by wolfejam » Fri, Feb 27, 2026, 7:12 PM UTC

verdverm wrote: post #4

wolfejam wrote: post #3

Earlier quoted context omitted.

Totally — git handles syncing files. The problem is these four files have different formats and conventions. Same project context, four dialects. That's why I wrote bi-sync --all: one YAML source, four native outputs.

that's not my experience, LLMs are flexible enough, ln -s is sufficient

Post by wolfejam » Fri, Feb 27, 2026, 7:21 PM UTC

verdverm wrote: post #6

wolfejam wrote: post #5

Earlier quoted context omitted.

ln -s makes all four files identical. Whichever format you write it in, the other three get the wrong structure. This generates each in its native format.

show me good evals that it actually makes a difference that is the opposite of what I see

Post by wolfejam » Sat, Feb 28, 2026, 4:05 PM UTC

verdverm wrote: post #8

wolfejam wrote: post #7

Earlier quoted context omitted.

ETH Zurich tested this: LLM-generated prose context = -3% performance, +20% cost. Even human-written = +4% at +19% cost. The problem is prose bloat. Structured formats avoid that by design. https://arxiv.org/abs/2602.11988

There is research that shows the opposite. A literature survey will show you something different than a single paper.