Juanpe /

ModelRelay

Composable AI workflows for Swift: small typed steps, a model per step, tools, MCP and on-device models

A new way for AI to search for data
View on GitHub
8GitHub stars

Swift, shell

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit ebd598da7c (2026-10-18).

Selected work

Juanpe Catalán
@Juanpe

“Centralize HTTP responses and prepare semantic releases”. 19 files, 665 lines in Tests, Sources, Scripts.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-24. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

aiapple-intelligencefoundation-modelsiosllmmacosmcpmlx

Example questions

The prompt

Paste it into your AI agent. It clones Juanpe/ModelRelay at the pinned commit and indexes it on your machine.

Search the GitHub repository Juanpe/ModelRelay with XERJ (https://hub.xerj.org/corpus/juanpe--modelrelay).
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/Juanpe/ModelRelay ModelRelay && git -C ModelRelay checkout ebd598da7ca200fdcdd4733602211b8278bc8365
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./ModelRelay --url http://127.0.0.1:9200 --prefix modelrelay --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.

Related

Juanpe CatalánAI, prompts and agents corporahaystacksimonw-llmgriptapenikiomori/PretypeSharpAI/SwiftLMn0mad-ai/bastra-recall

Selected work and consent: the XERJ registry.