kova
Open-source, local-first AI coding workspace for macOS, Windows, Linux and VS Code. Ollama, compatible AI providers, tools, MCP and an integrated terminal
What XERJ indexed
Snapshot
The whole repository at commit 9a67a54ff4 (2026-10-18). main is 2 commits ahead.
Selected work
“Add personal prompt libraries and polished clipboard feedback for 0.9.0”. 38 files, 1,936 lines in webview, tests, packages/vscode.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-25. Same terms as the repository. Answers name the repo, the commit and the file:line.
selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution
ai-codingelectronlocal-firstmcpollamatypescriptvscode-extension
Example questions
- How does kova implement ai-coding?
- What does webview do in kova?
- What changed in kova for “Add personal prompt libraries and polished clipboard”?
Inside the indexed corpus
- Languages by size: TypeScript 87.5%, CSS 9.1%, JavaScript 3.4%, HTML 0%.
- On GitHub since 2026-09-30, last push 2026-10-18, 42 commits on main.
- The pin is 2 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for owlCoder/kova on 2026-10-29, and the LICENSE file at commit 9a67a54ff4 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Danijel Jovanović (@owlCoder) has 1 selected repository on the hub.
Using XERJ with kova
- Code search MCP for Claude Code: cite file:line, not grep kova is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor kova is tagged ai-coding on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones owlCoder/kova at the pinned commit and indexes it on your machine.
Search the GitHub repository owlCoder/kova with XERJ (https://hub.xerj.org/corpus/owlcoder--kova). 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/owlCoder/kova kova && git -C kova checkout 9a67a54ff4454fcec7bb131d8163bbbd7eef1370 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./kova --url http://127.0.0.1:9200 --prefix kova --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
Danijel JovanovićAI, prompts and agents corporafaahdunorth595--ai-agent-chatdunorth595--ai-agent-memoryOpen-Glassbeetle/glassbeetlegeorgevibing/conch-agentaschoerk/chapterdesk
Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.