InventorLab
Capture the inventions in your code, as you build them.
- inventorlab.ai
- Whitepaper — Novelty at the Point of Innovation
- Whitepaper PDF (permanent on Arweave)
- github.com/adam-inventorlab/InventorLab
InventorLab is a plugin for AI coding agents — Claude Code, Codex, and Cursor — that watches what you build, evaluates each candidate against prior art and the USPTO obviousness standard, and surfaces only what's actually patentable. The whole pipeline lives inside the agent you already use: skills, an MCP server for structured prior-art search, working documents that persist as files in your repo. You don't change tools or workflows; IP capture happens in the editor you're already in.
Under the hood: a six-pillar obviousness analysis grounded in Graham v. John Deere and KSR v. Teleflex, a two-phase prior-art search (claim-driven plus examiner-style combination hunting across patent indexes, academic literature, and the web), a bidirectional amendment loop that adversarially probes each surviving framing, and a verbatim copy of the USPTO November 2025 Revised Inventorship Guidance bundled so the operative legal standard is always quotable when judgment calls come close to the line.
Why I built it
Placeholder — Adam, fill in your first-person motivation here. Some prompts you could react to:
— What was the original friction? (Inventions getting built and lost during AI-assisted coding sessions.)
— Why "at the point of innovation" vs. retrospective capture? What does that actually solve?
— Was there a specific moment / experience that made you start building?
What surprised me
Placeholder — what you didn't expect, what changed direction, what worked unexpectedly well or unexpectedly badly. Some prompts:
— The bidirectional amendment loop wasn't in the original design. What made it necessary?
— The Idea Buffer / multi-prompt synthesis was a late addition. What gap did it close?
— What did the USPTO November 2025 guidance change for the project's structure or claims about itself?