Hive

What is Hive?

Hive is an open-source runtime from the aden-hive project for teams of AI agents that handle repeatable business work. You describe an outcome to a queen, a long-lived agent with a role such as Growth or RevOps, its own memory and tools. She does one unit of the job herself to learn what it takes, saves that method as a skill, then fans the rest out to parallel worker agents. Each worker writes one row to a shared SQLite tracker, so the queen can query what is done and what is left, verify results and resume after a crash. Hive ships thirteen queen personas, built-in shell, file, browser and charting tools, any MCP server, cron and webhook triggers, and works with models from Anthropic, OpenAI, Gemini, OpenRouter, a local Ollama setup and more. It is licensed under Apache 2.0, free to run, and you pay only for the model you connect. Setup needs Python 3.11+, Node.js 20+ and git.

Use cases

• Run many similar jobs in parallel
• Research a list of products or accounts
• Process leads, tickets or documents
• Schedule agent runs by cron or webhook
• Audit and resume long agent runs
• Connect agents to MCP tools

Who it's for

• Developers building agent systems
• Growth and revenue operations teams
• AI engineers

Why use Hive

• The queen decides the shape of the work as it unfolds, so you do not draw a workflow graph in advance.
• A tracker on disk, not a context window, records what is done, so long jobs can be checked, audited and resumed.
• Workers run under tool-call budgets and the queen checks each row, which helps catch bad results before they reach you.
• You can pick any supported model or a local one, and workers can use a different model than the queen.
• The Apache 2.0 license and local install keep the software free and your data on your machine.

Hive features

• Queen agents with roles and persistent memory
• Parallel worker agents started with run_worker
• Shared SQLite tracker queryable with SQL
• Playbooks with retries, backoff and dead-letter lists
• Thirteen persona queens, six active by default
• Built-in shell, file, search, PDF, chart and CSV tools
• Browser Bridge extension for your own Chrome
• Skills in the open Agent Skills format
• Any MCP server added with hive mcp add
• Cron, interval and webhook triggers
• State saved to disk and resumed after a crash

Hive integrations

• Anthropic
• OpenAI
• Google Gemini
• Groq
• Cerebras
• OpenRouter
• Ollama
• Claude Code
• OpenAI Codex
• GitHub
• Gmail
• HubSpot
• Slack
• Notion
• Telegram

How to get started with Hive

1. Clone the repository and run the quickstart script, which sets up the environment, your model and the dashboard.
2. From the home screen, enter a task and pick which queen agent should handle it.
3. Approve the colony the queen proposes; she completes one unit, saves the method as a skill and starts parallel workers.
4. Review the tracker and the queen's checked answer, and re-run the playbook to pick up any rows still missing.

Hive limitations

• Requires Python 3.11+, Node.js 20+ and git
• You must supply a model, either an API key, a coding subscription or a local Ollama model
• Four workers run at a time by default
• On short histories, reading the full history can be more accurate than Hive's memory

Hive pricing

Hive is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Hive alternatives

The main Hive alternatives listed on Debuly are CrewAI, LangGraph, AutoGen, OpenAI Agents SDK, Hermes Agent and OpenHands. The table compares pricing and platforms; order is A–Z.

1. 

   AutoGen

   Microsoft's MIT-licensed Python and .NET framework for multi-agent AI apps, now archived; new projects are pointed to Microsoft Agent Framework.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit AutoGen (official site)
2. 

   CrewAI

   Multi-agent framework and platform for building AI agent crews in Python or a visual editor, then deploying and monitoring them.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit CrewAI (official site)
3. 

   Hermes Agent

   Free, MIT-licensed AI agent from Nous Research with persistent memory, auto-built skills, scheduling and chat-app access.

   Automation and agentsCodingProductivity
   Open sourceVisit Hermes Agent (official site)
4. 

   LangGraph

   Low-level open-source orchestration framework and runtime for building stateful, long-running AI agents as graphs.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit LangGraph (official site)
5. 

   OpenAI Agents SDK

   Open-source Python framework for building multi-agent workflows with tools, handoffs, guardrails, tracing, sandboxes and voice agents.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit OpenAI Agents SDK (official site)
6. 

   OpenHands

   Open-source AI coding agent platform with a free Agent Canvas, a Teams plan, and self-hosted Enterprise control

   CodingAutomation and agentsDeveloper platforms
   FreemiumVisit OpenHands (official site)

Hive FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from avatars.githubusercontent.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.