all-agentic-architectures and agentic-parallelism
The former, implementing various architectures, and the latter, detailing where to apply parallelism within agentic solutions, are complements because understanding how to parallelize is crucial for efficiently implementing and scaling the diverse agentic architectures described in the former.
About all-agentic-architectures
FareedKhan-dev/all-agentic-architectures
Implementation of 17+ agentic architectures designed for practical use across different stages of AI system development.
Implements 17+ architectures using LangGraph for stateful agent orchestration, with each pattern (Reflection, ReAct, Planning, Multi-Agent, Tree of Thoughts, etc.) demonstrated end-to-end in executable Jupyter notebooks. Features integrated evaluation via LLM-as-a-Judge for quantitative performance measurement and real-world scenarios spanning financial analysis, coding, and medical triage. Designed as a structured learning path progressing from single-agent enhancements through advanced multi-agent collaboration, memory systems, and self-aware agents with built-in safety mechanisms.
About agentic-parallelism
FareedKhan-dev/agentic-parallelism
Core concepts - where to apply parallelism in agentic solution
Implements 14 industrial-grade patterns for concurrent AI agent execution across tool calls, multi-agent teams, RAG pipelines, and fault tolerance using LangGraph and LangChain. Covers hierarchical task decomposition, competitive ensembles, speculative execution, hybrid search fusion, and redundant execution—each with instrumentation and state analysis. Targets enterprise-scale agentic systems requiring both latency reduction and reliability improvements.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work