harnessy-v2

Harnessy v2 capability harness

A new way for AI to search for data
View on GitHub
11GitHub stars

TypeScript, Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 70d2cffadc (2026-09-24).

Selected work

Julian Duru
@durutheguru

“add portable workspaces and verified offline relocation”. 21 files, 1,846 lines in packages/harnessy-core, 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 2026-10-22. 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

Example questions

The prompt

Paste it into your AI agent. It clones Flow-Research/harnessy-v2 at the pinned commit and indexes it on your machine.

Search the GitHub repository Flow-Research/harnessy-v2 with XERJ (https://hub.xerj.org/corpus/flow-research--harnessy-v2).
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/Flow-Research/harnessy-v2 harnessy-v2 && git -C harnessy-v2 checkout 70d2cffadc997dfbe8afabe9aa59d541b23c6c84
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./harnessy-v2 --url http://127.0.0.1:9200 --prefix harnessy-v2 --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

Selected work and consent: the XERJ registry.