nana
Tetromino-battler AI using parallel MCTS, bitboards and message passing architecture
A new way for AI to search for data
5GitHub stars
What XERJ indexed
Selected work
“work requesting MP-MCTS”. 11 files, 1,671 lines in cpp, scripts, the project root.
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
multi-agent-planningtetristetris-aicppmcts
Example questions
- How does nana implement multi-agent-planning?
- Where does nana handle “work requesting MP-MCTS”?
- What does cpp do in nana?
The prompt
Paste it into your AI agent. It clones nightcrab/nana at the pinned commit and indexes it on your machine.
Search the GitHub repository nightcrab/nana with XERJ (https://hub.xerj.org/corpus/nightcrab--nana). 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/nightcrab/nana nana && git -C nana checkout 08e3cebcb5a124216a9806e2dae24ece469a375c 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./nana --url http://127.0.0.1:9200 --prefix nana --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
Paul AndersonAI, prompts and agents corporacerealxerj-columnarbrpcdheerajshenoy/lektraYmsniper/umbraStartYR/CalculatorX
Selected work and consent: the XERJ registry.