Pi-Bolt

Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on…

A new way for AI to search for data
View on GitHub
563GitHub stars

TypeScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 219f6ee901 (2026-10-22).

Selected work

Krish Bansal
@KrishBnsl

“add /usage command”. 7 files, 908 lines in packages/coding-agent.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

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

ahead-of-timebuncoding-agentlinuxperformancepiai-agentai-coding-assistant

Example questions

The prompt

Paste it into your AI agent. It clones opensec-git/Pi-Bolt at the pinned commit and indexes it on your machine.

Search the GitHub repository opensec-git/Pi-Bolt with XERJ (https://hub.xerj.org/corpus/opensec-git--pi-bolt).
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/opensec-git/Pi-Bolt Pi-Bolt && git -C Pi-Bolt checkout 219f6ee9013cd137fc908e410b13c4d92dc6e3e5
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./Pi-Bolt --url http://127.0.0.1:9200 --prefix pi-bolt --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

Selected work and consent: the XERJ registry.