behavioral-testing

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.

Prove web features work in a real browser—with persistence, source-of-truth, replay, and CI evidence.

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

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

Claude Code skill: measures whether agents actually follow skills, rules, and agent definitions — automated behavioral compliance testing

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

Execution-grounded semantic clone detection for JS/TS — finds functions that behave the same but are written differently, then runs them in a sandbox to prove which one is wrong.

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

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.

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

Offline detection-as-code lab for original Sigma rules, synthetic behavioral tests, ATT&CK mapping, coverage analysis, and pySigma query conversion.

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

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

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

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

AI persona-based behavioral testing for web apps. No test scripts. YAML-configured. Vision-powered.

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

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.

Behavioral regression testing across LLMs by task type