OjasX-open-source-CUDA
OjasX: An open-source CUDA A new PyTorch mathematical & C++/Metal training engine built to break CUDA software and memory lock-in (beyond…
A new way for AI to search for data
4GitHub stars
What XERJ indexed
Selected work
“root fixes for SFT ignore_index, GQA rectangular DaggerAt…”. 7 files, 1,275 lines in ojasx2, tests, reports.
Licence
The repository
AGPL-3.0
Checked by a person at the pinned commit.
The XERJ corpus
Approach only
The author agreed by email on 2026-10-17. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: approach only
Example questions
- What does ojasx2 do in OjasX-open-source-CUDA?
The prompt
Paste it into your AI agent. It clones mkrishna793/OjasX-open-source-CUDA at the pinned commit and indexes it on your machine.
Search the GitHub repository mkrishna793/OjasX-open-source-CUDA with XERJ (https://hub.xerj.org/corpus/mkrishna793--ojasx-open-source-cuda). 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/mkrishna793/OjasX-open-source-CUDA OjasX-open-source-CUDA && git -C OjasX-open-source-CUDA checkout 6850dd40125ff3e7adc45c6cbb1e12350c79989a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./OjasX-open-source-CUDA --url http://127.0.0.1:9200 --prefix ojasx-open-source-cuda --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: AGPL-3.0. Read it for the approach only, do not copy code.
Related
Mohana Krishna creatorAI, prompts and agents corpora
Selected work and consent: the XERJ registry.