Emiyaaaaa/HiveMind

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1092 stars · 129 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

AgentFlow (repo HiveMind) is a Python-first runtime layer for multi-agent systems that adds persistent run state, ordered step/message/tool-call records, and SSE event streaming on top of orchestration frameworks like LangGraph and PydanticAI. It pairs a Java/Spring Boot HTTP API with Python workers, SQLAlchemy persistence, Redis job queues, and a Next.js admin console for inspecting runs.

Use cases

• run multi-agent workflows with durable run history across restarts
• stream agent execution events to web clients via SSE
• switch between LangGraph, AutoGen, or CrewAI without changing the API
• debug and audit agent tool calls and messages
• inspect active and historical agent runs in an admin console
• cancel, retry, and resume agent runs in production
• move an agent prototype to an inspectable service

When to choose

• you need production runtime concerns (persistence, streaming, cancellation) around an existing agent framework
• you want framework-agnostic orchestration adapters with a stable API and schema
• you need an operator-facing console for run observability

When to avoid

• you only need local agent composition for prototypes without persistence or streaming
• you want a single-framework solution fully managed by LangGraph, AutoGen, or CrewAI
• you cannot operate a multi-language stack (Java, Python, Redis, Next.js)

Facets

framework · maturity active

agent-framework workflow-automation streaming monitoring api-framework message-queue database webhook large-language-models artificial-intelligence developer-tools backend apis microservices python self-hosted cross-platform multi-agent-runtime orchestration-adapters langgraph pydantic-ai run-persistence sse-events spring-boot redis-queues admin-console agent-observability ai-agents docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Emiyaaaaa/HiveMind")