FreedomIntelligence / MyPhoneBench Star 24 Code Issues Pull requests MyPhoneBench: Do Phone-Use Agents Respect Your Privacy? personal-ai-agents agent-benchmarking phone-use-agents mobile-gui-agents privacy-aware-agents behavioral-privacy verifiable-evaluation Updated Apr 3, 2026 Python
sholajegede / mastra-vs-langchain Star 15 Code Issues Pull requests The same AI agent pipeline built in Mastra and LangChain. Runs in parallel, measures everything. real-time typescript nextjs ai-agents convex langchain anthropic llm-evaluation langgraph tavily mastra agent-benchmarking Updated Jun 6, 2026 TypeScript
ather-techie / ai-agents-design-patterns Star 10 Code Issues Pull requests 20 runnable LLM agent design patterns in Python, benchmarked, traced, offline-compatible. ReAct, multi-agent, constitutional AI, and more. python design-patterns multi-agent-systems anthropic claude-ai llm-agents react-agent agentic-ai agent-orchestration agent-benchmarking Updated Jul 4, 2026 Python
lirantal / coding-agent-security-benchmark Star 1 Code Issues Pull requests A Claude Agent SDK security benchmark project ai-agents agentic-workflow agentic-ai claude-code agent-benchmark agent-research claude-opus-4-6 agent-benchmarking Updated Jun 14, 2026 TypeScript