Nguyễn Ngọc Hải

What an agent can do with the Evolo corpus

hiinguyen/Evolo: Scores your GitHub contributions with an AI judge and a deterministic XP formula

• Look up how Evolo implements achievements, ai, cli, with answers cited to file and line.
• Reuse a worked example: the commit “publish the CLI on npm and run it on macOS and Windows” (9 files · JavaScript).
• Answer from Evolo's real JavaScript source instead of memory (AI, prompts and agents).

• Where does Evolo handle “publish the CLI on npm and run it on macOS and Windows”?
• How does Evolo implement achievements?
• What does packages/cli do in Evolo?

Search the GitHub repository hiinguyen/Evolo with XERJ (https://hub.xerj.org/corpus/hiinguyen--evolo).
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/hiinguyen/Evolo Evolo && git -C Evolo checkout 78e85e85b0eab219406d1b440971b7441e5baf58
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Evolo --url http://127.0.0.1:9200 --prefix evolo --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.

corpus hiinguyen--evolo · AI, prompts and agents
Related corpora: agno, aider, PraiseTechzw/autopilot-cli, nyaomaru/changelog-bot
AI search and retrieval with XERJ · Case study: reference coding for agents