hive

A multi-agent execution framework designed for AI tasks in production environments.

Agent SkillDevOpen sourcemulti-agentproduction-aistate-managementfailure-recoveryobservability

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 10.6k
Source: skill-github
Repository: github.com/aden-hive/hive

Overview

Hive is a zero-configuration, model-agnostic execution framework that dynamically generates multi-agent topologies to handle complex, long-running business workflows. By simply defining a goal, the runtime compiles a strict graph-based execution DAG that securely orchestrates specialized agents to execute concurrent tasks in parallel. It supports persistence, role-based memory that evolves with project context, ensuring deterministic fault tolerance, deep state observability, and seamless asynchronous execution.

Capabilities

▪Multi-agent coordination for parallel task execution
▪Graph-based execution of complex workflows
▪Role-based memory evolving with project context
▪Zero configuration, no technical setup required
▪General-purpose computing and browser usage
▪Custom model support

Use cases

State persistence and crash recovery for long-running agentsCost enforcement, observability, and audit trails for production workloadsAgents with self-repairing capabilities through fault capture and graph evolutionMulti-agent coordination with session isolation and shared buffers

Setup

Requires: Python 3.11+

Refer to the official documentation for installation and configuration: https://docs.adenhq.com/getting-started/quickstart

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Who is Hive suitable for?

Teams looking to move AI agents from prototype to production.

Does Hive support custom models?

Yes, Hive supports custom models.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP