Public information
For agents.
EXPLORE FAILURE is an independent AI lab building public tools and experiments around AI systems, local computation, evidence, and continuity of work.
Readable resources
The same page content supplies these resources and the website. The project data distinguishes public releases from research and links release-scoped evidence.
Project status
- Harness Workbench — Public release · v0.2.0
Give your local model and coding agent a real job. Harness Workbench checks the result independently, keeps the evidence, and saves a Recipe you can run again. The agent saying “done” doesn’t earn a pass.
- Portable proof — In development — unreleased
The claim can travel without pretending its uncertainty disappeared.
- The downloadable research lab — In development — unreleased
Reopen the research as working practice, not merely as a report.
- Work Engine — Exploring the idea — unreleased
EXPLORE FAILURE is working toward a future where you choose your models, control your data, and keep the work you build. Start locally, borrow compute when needed, and carry your progress with you as tools and providers change.
Author: Garrett Davis.