ashhart /

TensorFold

LLM Inference Engine for Metal and CUDA

A new way for AI to search for data
View on GitHub
1,474GitHub stars

Zig, Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit d58765718a (2026-10-18).

Selected work

Christian Schröder
@cwschroeder

“Flash Next on Metal: requests on shared sessions sized to the traffic…”. 41 files, 3,383 lines in zig, tools, the project root.

Licence

The repository

Apache-2.0

Checked by a person at the pinned commit.

The XERJ corpus

Apache-2.0, with credit

The author agreed by email on 2026-10-23. 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

aiai-toolsllmllm-inferencellm-tools

Example questions

The prompt

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

Search the GitHub repository ashhart/TensorFold with XERJ (https://hub.xerj.org/corpus/ashhart--tensorfold).
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/ashhart/TensorFold TensorFold && git -C TensorFold checkout d58765718a0e1a0524a64fa04510d4b3cfef815b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./TensorFold --url http://127.0.0.1:9200 --prefix tensorfold --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: Apache-2.0. Keep the copyright notice and credit the authors.

Related

Christian SchröderAI, prompts and agents corporaguardrailsagentopshaystackzendev-sh/goaidelphisecurity/xaidreshanized/M31A

Selected work and consent: the XERJ registry.