# area-o1 / dashboard
Local-first · Evidence engine
Area O1
An O-1A / EB-1A evidence file, built on your own computer — every claim traced to its source.
- Evidence inbox pulls from GitHub, Hugging Face, Semantic Scholar, OpenAlex, arXiv and ORCID
- Every fact is a claim quoting its source word for word
- Runs on 127.0.0.1 — no account, no server, no telemetry
Profile · O-1A
Criteria scoreboard
- Original contributions3 evidencebanked
- Scholarly articles2 evidencebanked
- Judging the work of others1 evidencebuilding
- Critical role1 evidencebuilding
- Press about the work0 evidencegap
- Awards0 evidencegap
an invitation never counts as done
- Evidence inbox pulls from GitHub, Hugging Face, Semantic Scholar, OpenAlex, arXiv and ORCID
- Every fact is a claim quoting its source word for word
- Runs on 127.0.0.1 — no account, no server, no telemetry
- MCP server lets Claude Code or Codex read the case without changing it
What it does
Area O1 turns your work into a living evidence file for an extraordinary-ability case. A criteria scoreboard marks each O-1A or EB-1A criterion as banked, building or a gap — and an invitation never counts as a completion. An evidence inbox proposes items from GitHub, Hugging Face, Semantic Scholar, OpenAlex, arXiv, ORCID and any web page; nothing counts until you accept it.
Memory you can trace
Every fact is a claim quoting its source word for word, drawn as a sky you can click back to the raw page. Rule statements are checked against official sources that refresh when a rule actually changes, and letter drafts are built only from approved claims.
Private by construction
The dashboard is served only to your own machine. Your case is a folder of plain files in its own git repo. Gmail access is read-only, and nothing sends without your approval. Claude Code and Codex can read the case over MCP, but they can't change your evidence.