onsystem
Keeps coding agents on your design system: catches palette colors, native elements and APIs your system lacks, at every edit and pull request, with the fix. Set it up once in your design-system package; every app in your monorepo gets it
What XERJ indexed
Snapshot
The whole repository at commit 3390a64587. It is the newest commit on main.
Selected work

Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-28. 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-agentsdesign-systemdesign-tokenslintermcpmodel-context-protocolreactshadcn-ui
Example questions
- How does onsystem implement ai-agents?
- Show the design-system code in onsystem.
Inside the indexed corpus
- 3,085 files, 14.8 MB in total, about 4.9 KB per file.
- Languages by size: TypeScript 94.4%, JavaScript 5.4%, CSS 0.2%, Python 0.1%.
- On GitHub since 2026-10-06, last push 2026-10-30, 692 commits on main.
Licence on GitHub and in the corpus
GitHub reported MIT for dgesteves/onsystem on 2026-10-31, and the LICENSE file at commit 3390a64587 was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Diogo Esteves (@dgesteves) has 3 selected repositories on the hub.
Their other repository pages: dgesteves/signoff-ui, dgesteves/ondocs.
Using XERJ with onsystem
- Code search MCP for Claude Code: cite file:line, not grep onsystem is tagged mcp on GitHub.
- What is an MCP memory server?
- A local search tool for Codex and Cursor onsystem is tagged claude-code on GitHub.
- Local code search MCP that uses fewer tokens than grep
The prompt
Paste it into your AI agent. It clones dgesteves/onsystem at the pinned commit and indexes it on your machine.
Search the GitHub repository dgesteves/onsystem with XERJ (https://hub.xerj.org/corpus/dgesteves--onsystem). 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/dgesteves/onsystem onsystem && git -C onsystem checkout 3390a6458709488a5c0a4c8424f8b2c11cc206b8 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./onsystem --url http://127.0.0.1:9200 --prefix onsystem --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
Diogo EstevesAI, prompts and agents corporareact-spectrumcarbonharperMartaCondeDesign/helixdsuday-a/uipkge-registryAndreyBegma/glass-ui
Stats: GitHub API, fetched 2026-10-31. Snapshot: the git tree at the pinned commit. Selected work and consent: the XERJ registry.