Agent Behavior

Studying the gap between what agents know and when they act on it.

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

Reverse engineer anything with agents, from app behavior down to native binaries.

Behavior-guardrail hooks for Claude Code: test-tampering + outbound-action guards

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.

Deletion-first Agent Skill for removing test bloat, verification theater, and speculative fallbacks while preserving behavior.

Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to website traffic, user behavior, and performance data with schema discovery, server-side aggregation, and safe defaults that reduce data wrangling.

PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstream behavior is the contract, and Go is the implementation language.