browser-use/browser-use-pi
Four days old and already worth dissecting: a minimal, evaluation-driven browser agent — small enough to fully understand.
Activity
Pushed Sep 9; a 4-day-old repository.
What to Study
The minimal browser control loop, eval-driven hill climbing, action representation, and failure recovery.
Why It Matters
Small enough to fully dissect; its evaluation-driven design is more valuable than another giant framework.
Action
Fork; run browser evals; mutate one policy/tool boundary and measure task success.
Notes
- Study the minimal browser control loop and eval-driven hill climbing
- Candidate for the Eval-Hill-Climbed Browser Agent experiment
AutoNateAI Experiments Using This
ProposedProcedural Graph Runtime
Can a validation-gated, self-evolving execution graph improve long-horizon agent workflows without increasing unsafe tool use?
hub Inspectable Agent Systems
ProposedIndependent Test Agent
Does separating an independent Test agent from a Repair agent reduce false-confidence patches without hurting resolution rate?
hub Inspectable Agent Systems
ProposedRevocable Memory Graph
Can a graph-based retriever enforce memory revocation structurally while still preserving useful personalized context?
hub Inspectable Agent Systems
ProposedSafety Judge Stress Lab
Which content-invariant wrapper transformations produce the highest disagreement across automated safety judges, and can simple ensembles resist them?
hub Inspectable Agent Systems
ProposedContext Graph vs. Context Database
Does explicit graph structure improve retrieval traceability and multi-hop reasoning over a context-database approach, at the same token cost?
hub Inspectable Agent Systems