Papercusp.
The world's first truly self-improving agent harness.
Agents that grade their own work, mine the results for what to fix, turn it into work, and drain the queue — then grade the next lap. The loop runs on any project. Including the one that builds Papercusp.
Private access · onboarding by invitation
One full lap, captured live.
An Opus agent grades a Sonnet agent, the scorecard breeds an idea, the idea becomes work, and a fleet drains it — recorded on a real desktop, no mockups. Final cut landing soon.
One live lap — grade → ideas → work → fleet — at 1920×1080, terminal text kept razor-sharp.
Self-hosted from the exact encoded master (Cloudflare R2, no re-encode) so the terminal text stays razor-sharp — video platforms re-compress and smear fine text, which is the one thing this demo can't lose.
One closed loop, running continuously — or human-directed sessions through SU agents.
Most harnesses run agents. Papercusp runs the loop that makes the agents better — every stage is a real, inspectable surface in the product.
Grade the work
A grader agent re-verifies another agent's run against a rubric and files a scorecard — every rating carries evidence.
Breed ideas
The blender mines scorecards and observations into concrete improvement ideas: what should exist, what keeps failing.
Make it work
Ideas become work items on a plan; a fleet pulls the queue, and changes pass a test gate before they land.
Keep the gain
What worked is retained and measured next lap. The bar only moves one way.
Papercusp is just another project inside Papercusp — and can use its self-improvement framework like any other.
The self-improvement loop isn't a feature bolted onto one workflow — it's the substrate. It applies to any project the harness manages, including its own codebase. The system you're looking at improved itself to get here.
Every stage is a real surface — not a diagram.
Ten captures from the live product and terminal. Each screenshot slot below is annotated with what it shows; the two terminals render real command text to prove it stays legible.
See the loop run on your own work.
Papercusp is in private access while we onboard partners one at a time. Tell us what you'd point it at, and we'll set you up.
access@papercusp.com