Studying the gap between what agents know and when they act on it.
Curated kinds of behavior
Canonical home for AI Behavior Science research and the Founding Territory Paper
Behavioral design specs for AI agents. Named patterns, cognitive science, forkable skills.
Reviews and modernizes stacks, packages, SDKs, and tooling before code is written against them.
RL-style eval measuring intent/action divergence in frontier agents: model acknowledges a correction, then acts on the stale value anyway. 3 scenarios, 371 trials on claude-haiku-4-5, Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro Preview.
MCP server for AI agent research — captures LLM reasoning, model identity, and feedback via schema injection
Scores and improves prompts for clarity, consistency, signal density, structure, and runtime fit.
Produces auditable token-usage and cost reports from runtime evidence, normalized usage bundles, and repository-level report sets.
High-performance routing engine that selects the best agent skill for a task and emits structured handoff decisions.
Audits frontend implementations for design-system drift across CSS, Tailwind, JSX, TSX, Vue, and Angular code.
Manages durable cross-agent shared memory for stable conventions, reusable policies, and organization-wide operating rules.
An easy-to-integrate Unity FSM for basic enemy AI behaviors, utilizing ScriptableObject for customizable and reusable AI states like Idle, Chase, and Attack.
Audits APIs against OpenAPI, AsyncAPI, JSON Schema, protobuf, or PRD contracts to catch drift before release.
Add a description, image, and links to the agent-behavior topic page so that developers can more easily learn about it.
To associate your repository with the agent-behavior topic, visit your repo's landing page and select "manage topics."