FluxVLA

An all-in-one VLA engineering platform for embodied AI: from data to real-robot deployment

A new way for AI to search for data
View on GitHub
756GitHub stars

Python

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 9b827f8665 (2026-10-19).

Selected work

Yinhao Li
@yinchimaoliang

“[Fix] Stabilize DreamZero training and RoboCasa evaluation”. 18 files, 1,420 lines in fluxvla, configs, test.

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 2026-10-20. 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

real-robotsreal-timeroboticsvision-language-action-modelvlmworld-action-modelembodiedai

Example questions

The prompt

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

Search the GitHub repository FluxVLA/FluxVLA with XERJ (https://hub.xerj.org/corpus/fluxvla--fluxvla).
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/FluxVLA/FluxVLA FluxVLA && git -C FluxVLA checkout 9b827f86653c4051b1b1722fe19e178f1170c9ba
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./FluxVLA --url http://127.0.0.1:9200 --prefix fluxvla --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

Selected work and consent: the XERJ registry.