Code

Agent4Agents (Project Compact) tackles four common failure modes in agentic coding — bogus work, architectural re-litigation, decision fatigue, and token waste — by enforcing project rules mechanically rather than relying on prompts. It uses a cache-aligned context prefix, append-only architectural decision records (ADRs), tier-adaptive ceremony, and server-side enforcement via compact-check in CI with no admin bypass. Written in Python; pairs with gstack as the workflow engine.

This repository contains a code snippet that first extracts key frames from a video using ffmpeg. Then it stitches frames by constructing a binary tree of consecutive keyframes till all the frames are merged into a single summary notes slide.

This repository contains code snippets for generating optical flow estimation stimuli. These stimuli are primarily developed by the neuroscience/psychophysics communities to characterize motion perception in humans/primates.