Community-driven behavioral reliability benchmark for LLMs. 231 probes across 19 modules, deterministic scoring, perplexity correlation, layer sensitivity mapping, quant method capture, hardware-stratified community rankings. Every test contributes to the community dataset.

Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).

Behavioral regression testing for LLMs — diff, drift, fingerprint. Zero deps.

Behavioral browser-spec layer for agent-in-session use. Specs declare intent+outcomes; agents execute + heal via agent-browser or Playwright. CLI + MCP server, agent-neutral.

Model behavioral diffing - compare LLM outputs across versions, detect regressions.

LLM drift detector — know within 5 min when GPT-4o, Claude, or Gemini silently changes behaviour. Open source, self-hostable.

Bots I broke and how I broke them to be a future conversational Red Teamer

Leak™ — behavioral constraint testing for AI agents. Find your drips before the puddle forms.

🐦 Behavioral smoke tests for deployed AI agents — probes every 15 min, alerts on drift

Advanced Mockito usage featuring Spies, Mocks, and behavioral verification to test a shopping cart checkout flow.

How does a model behave when nobody told it what to do? This protocol observes LLM defaults before asking about preferences, then packages the findings into a reusable profile. Works on local Ollama models and cloud APIs alike.

Agent behavioral testing -- YAML specs for tool calls, sequences, constraints

Artifacts for arXiv:2606.28430. Task spec, prompts, 18-run agent corpus, and a deterministic audit tool from a study showing two production LLM coding agents (Copilot CLI · claude-opus-4.7, gpt-5.5) score near-perfect on a hidden 222-test oracle while leaving the requested library dead or absent.

Regression testing CLI for AI agents — define expected behaviors in YAML, run in CI, fail deploys on behavioral drift

Behavioral regression testing across LLMs by task type

Production-grade LLM evaluation framework measuring model behavior across 5 dimensions with human-vs-LLM judge agreement validation and Cohen's Kappa scoring

ModelGuard — Behavioral Contract Monitor for LLMs. Paste your contracts, see which break when your model silently updates.

Diff and regression-detect LLM agent execution traces

Catch AI behavioral regressions before merge. Run eval suites for prompts, agents, and workflows in GitHub Actions.