pikabaka
Open-source AI interview copilot & meeting assistant. Real-time transcription, AI-suggested answers, screenshot reasoning. BYO API key, or run fully offline with Ollama. macOS + Windows
What XERJ indexed
Snapshot
The whole repository at commit ecbec37f3c (2026-10-29). main is 78 commits ahead.
Selected work
“edit the role and task prompts in Settings”. 15 files, 827 lines in test, electron, src/components.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-29. Agents read it for how it works, not to copy it. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: approach only
aiai-assistantclaudecluely-alternativeelectrongeminigroqinterview-copilot
Example questions
- How does pikabaka implement ai?
- Where does pikabaka handle “edit the role and task prompts in Settings”?
- What does electron do in pikabaka?
Inside the indexed corpus
- Languages by size: TypeScript 93.5%, Rust 3.9%, JavaScript 1.8%, CSS 0.8%, HTML 0%.
- On GitHub since 2026-03-27, last push 2026-10-31, 408 commits on main.
- The pin is 78 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported AGPL-3.0 for royisme/pikabaka on 2026-10-31, and the LICENSE file at commit ecbec37f3c was reviewed as AGPL-3.0. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Roy Zhu (@royisme) has 1 selected repository on the hub.
Using XERJ with pikabaka
- RAG without a vector database: one hybrid index The hub files it under AI, prompts and agents.
- Index a reference library for a coding agent
- ripgrep vs a code index for coding agents: 30 tasks
- Best MCP servers for local code search in 2026, compared
The prompt
Paste it into your AI agent. It clones royisme/pikabaka at the pinned commit and indexes it on your machine.
Search the GitHub repository royisme/pikabaka with XERJ (https://hub.xerj.org/corpus/royisme--pikabaka). 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/royisme/pikabaka pikabaka && git -C pikabaka checkout ecbec37f3cab536cfebe0cc44154b6787d328a7a 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./pikabaka --url http://127.0.0.1:9200 --prefix pikabaka --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
Roy ZhuAI, prompts and agents corporagriptapeagentopsxobotyi--cc-foundry-infrastructuresotger/allai-chatThinkInAIXYZ/deepchatgemkids275/AIShortcuts
Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.