Back to directory

EggAI Multi-Agent Meta Framework

An async-first, distributed framework for building multi-agent systems in Python, with an SDK for agent-to-agent communication, example integrations with frameworks such as LangChain, DSPy and LiteLLM, and a demo multi-agent insurance support system.

EggAI Multi-Agent Meta Framework

EggAI is a meta framework for building multi-agent systems in Python, aimed at enterprise-grade deployments with quality-controlled output. It provides an SDK that abstracts agent definition and agent-to-agent communication in an async-first, distributed and composable architecture, independent of any single AI framework.

It ships with a set of examples showing integration with tools such as DSPy ReAct agents, LangChain, LiteLLM, a WebSocket gateway, and guardrails for toxicity and PII leakage, plus a working multi-agent insurance support demo that handles billing inquiries, claims processing and policy lookup through retrieval-augmented generation.

It is written in Python and licensed under MIT.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.