Eltarras /

thunc

Call an LLM like a typed Python function. Docstring is the prompt, return type is the contract

A new way for AI to search for data
View on GitHub
3GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit da73316005 (2026-10-16).

Selected work

Hussein Eltarras
@Eltarras

“Recordings survive a thunc upgrade”. 4 files, 399 lines in tests, thunc.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-20. 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

aianthropicclaudellmllm-functionsprompt-engineeringpythonstructured-output

Example questions

The prompt

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

Search the GitHub repository Eltarras/thunc with XERJ (https://hub.xerj.org/corpus/eltarras--thunc).
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/Eltarras/thunc thunc && git -C thunc checkout da733160057b2942589c7b39134354fe8f775b4c
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./thunc --url http://127.0.0.1:9200 --prefix thunc --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

Hussein EltarrasAI, prompts and agents corporagriptapehaystackinstructorEverMind-AI/Ravenyasik/agentlanefelipesotero/opencode-hard-limit

Selected work and consent: the XERJ registry.