igmarin /

rails-ai-bridge

Zero-config MCP server that gives AI assistants live, read-only knowledge of Rails apps

A new way for AI to search for data

View on GitHub

16GitHub stars

325commits on main

2forks

v5.4.0latest release, 2026-10-24

Ruby 99.9%, Shell 0.1%, HTML 0% · created 2026-03-21 · last push 2026-10-24

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit ced03340e7. It is the newest commit on main.

Selected work

Ismael Marín
@igmarin

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-28. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

rails-airails-ai-assisted-development

Example questions

How does rails-ai-bridge implement rails-ai?
Show the rails-ai-assisted-development code in rails-ai-bridge.

Inside the indexed corpus

Languages by size: Ruby 99.9%, Shell 0.1%, HTML 0%.
On GitHub since 2026-03-21, last push 2026-10-24, 325 commits on main.

Licence on GitHub and in the corpus

GitHub reported MIT for igmarin/rails-ai-bridge on 2026-10-29, and the LICENSE file at commit ced03340e7 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.

Contributors

Ismael Marín (@igmarin) has 9 selected repositories on the hub.

Their other repository pages: igmarin/rails-agent-skills, igmarin/elixir-phoenix-skills, igmarin/ruby-core-skills, igmarin/pi-vida, igmarin/agnostic-planning-skills, igmarin/dotfiles.

Using XERJ with rails-ai-bridge

RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
Ask questions about a GitHub repo without cloning it
Index a reference library for a coding agent
ripgrep vs a code index for coding agents: 30 tasks

The prompt

Paste it into your AI agent. It clones igmarin/rails-ai-bridge at the pinned commit and indexes it on your machine.

Search the GitHub repository igmarin/rails-ai-bridge with XERJ (https://hub.xerj.org/corpus/igmarin--rails-ai-bridge).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/igmarin/rails-ai-bridge rails-ai-bridge && git -C rails-ai-bridge checkout ced03340e7a5a69a21b6594072ee0d854a52ac81
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./rails-ai-bridge --url http://127.0.0.1:9200 --prefix rails-ai-bridge --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Ismael Marín AI, prompts and agents corpora licensee fluentd cfn-nag usetrmnl/trmnlp igmarin/ruby-core-skills fetijashari/permission_forge

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.