CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observation, clean-room reimplementation, and behavioral verification.

sandboxing ai-agents reverse-enginnering black-box-testing playwright model-context-protocol behavioral-testing specification-generation clean-room-reimplementation software-reimplementation

• Updated Nov 3, 2026
• Python

AgentBehaviorBench (ABB): A benchmark for evaluating AI agents’ ability to test other agents and detect behavioral defects.

benchmark llm-agents agent-evaluation agent-testing behavioral-testing multi-agent-benchmark agent-behavior-benchmark agent-behaviour-bench

• Updated Nov 7, 2026
• Python

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.

benchmark mcp community-driven model-evaluation ai-evaluation llm ollama sycophancy hallucination-detection llm-testing hardware-benchmark ai-trust trust-scoring behavioral-testing llm-benchmark deterministic-scoring

• Updated May 4, 2026
• Python

Runtime behavioral contracts for AI agents: define YAML contracts, check adapter outputs, and raise explicit contract violations. Agent Behavioral Contracts (ABC).

python yaml formal-verification ai-agents drift-detection runtime-enforcement behavioral-testing agent-reliability ai-reliability qualixar agent-contracts

• Updated Oct 2, 2026
• Python

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.

nodejs javascript typescript ai static-analysis code-analysis ast ci-cd embeddings openai developer-tools code-review software-engineering code-quality semantic-analysis clone-detection code-duplication behavioral-testing

• Updated Oct 31, 2026
• TypeScript

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

testing cli open-source typescript ai mcp developer-tools quality-assurance ai-agents e2e-testing playwright behavioral-testing

• Updated Jul 26, 2026
• TypeScript

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

saas gemini openai regression-testing gpt claude mlops drift-detection production-ml model-testing ai-monitoring llm llmops prompt-testing llm-monitoring llm-observability behavioral-testing

• Updated Aug 18, 2026
• Python

Executable behavioral contracts and hidden-evaluation harness for coding agents across nine software domains.

benchmark software-engineering coding-agents behavioral-testing

• Updated Sep 30, 2026
• Python

🩺 Behavioral testing for skill triggers — diagnose why a skill never fires (or fires too often), prescribe a fixed description, save a regression suite. One SKILL.md, 79 agents (Claude Code, Hermes, Codex, Gemini...)

testing skills evaluation developer-tools cursor regression-testing agents codex ai-agents windsurf skill-evaluation ai-tools github-copilot llm prompt-engineering gemini-cli agent-skills claude-code behavioral-testing trigger-testing

• Updated Oct 9, 2026
• Python

Understand the mechanism. Rebuild the behavior. Prove the result. Independent reverse-engineering MCP, skill and CLI for Claude Code and Codex: artifact analysis, experiment planning and behavioral verification.

electron javascript debugging mcp static-analysis reverse-engineering developer-tools browser-extension rea codex ai-agents manifest-v3 agent-skills vibe-coding claude-code behavioral-testing claude-skills reverse-engineer-anything software-reconstruction rea-pro-max

• Updated Nov 11, 2026
• JavaScript

A toolkit for controlled behavioral evaluation of LLMs

model-evaluation ai-safety llm-evaluation llm-testing behavioral-testing

• Updated Nov 9, 2026
• Python

Static analyzer for React tests that finds UI behaviors exercised but not explicitly verified. Testing Library, Jest/Vitest, and Material UI.

react typescript jest material-ui static-analysis test-coverage code-quality mui frontend-testing testing-library react-testing-library vitest ai-testing test-quality behavioral-testing

• Updated Aug 31, 2026
• TypeScript

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

python testing regression-testing model-evaluation llm behavioral-testing

• Updated Apr 11, 2026
• Python

Agent Skill for Claude Code that measures whether coding agents actually follow a skill, rule or agent definition: it generates scenarios from supportive to competing prompts, runs an agent on each, and reports compliance rates with classified tool call timelines.

evaluation compliance ai-agents anthropic agent-skills claude-code behavioral-testing claude-skills claude-skill agent-skill

• Updated Nov 7, 2026
• Python

Behavioral regression testing for AI applications: repeat LLM, agent and RAG test cases, and tell real regressions from noise.

nodejs testing cli typescript regression-testing ai-agents rag github-actions llm ai-testing evals llm-evaluation llm-as-a-judge llm-testing behavioral-testing

• Updated Oct 1, 2026
• TypeScript

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

python nlp machine-learning evaluation regression-testing fingerprinting model-comparison drift-detection llm behavioral-testing

• Updated Apr 10, 2026
• Python

Open-source behavioral contract testing for AI agents. Define critical behavior, run the real agent, and catch regressions.

nodejs typescript ai-agents ai-tools ai-agent agentic-workflow agentic-ai model-context-protocol agent-evaluation agent-testing behavioral-testing

• Updated Aug 31, 2026
• TypeScript

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.

typescript mcp browser-testing ai-agents bun e2e-testing playwright behavioral-testing agent-browser

• Updated Oct 15, 2026
• TypeScript

python machine-learning neuroscience computational-neuroscience cognitive-science mne-python biomedical-engineering eeg-analysis stroop-test neurotechnology behavioral-testing erp-analysis

• Updated Oct 3, 2026
• Python

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

mockito junit5 java-testing behavioral-testing spy-vs-mock

• Updated Feb 15, 2026
• Java