I built Manas to solve challenges I faced in my PhD research on formally verified systems for LLM applications. After repeatedly implementing similar patterns for agent orchestration, I decided to create a reusable framework.

What makes Manas different is its approach to multi-agent workflows. It implements a think-act-observe cycle for agents with proper state persistence, while providing visualizable workflow orchestration between specialized agents. The core flow execution logic is formally verified, which was critical for my research.

Interestingly, I "vibe coded" much of Manas - using LLMs to generate code while I guided the architecture. This meta approach of using LLMs to build LLM orchestration tools proved surprisingly effective.

The framework is provider-agnostic (OpenAI, Anthropic, HuggingFace, Ollama) and includes vector store integrations (FAISS, Chroma, Pinecone) for RAG applications. Everything is async-first with proper error handling.

The docs include several examples to get you started: https://manas.koley.in

GitHub: https://github.com/arkokoley/manas

I would love to hear your thoughts!