# aden-hive/hive

Multi-Agent Harness for Production AI

Repository: https://github.com/aden-hive/hive
Canonical: https://ross.abutalabs.com/products/hive
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, agent-framework, agent-skills, anthropic, automation, autonomous-agents, claude, human-in-the-loop, openai, python, self-hosted, self-improving, harness, harness-engineering
Last push: 2026-08-21T05:30:06+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 81, longevity 16
- inputs: {"age_days": 234, "days_push": 12, "days_rel": 124, "gap_med": 2.0, "n_releases_24m": 37}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10974, forks 5672 (observed 2026-08-28T04:10:44.926107+00:00)

## What it is
OpenHive is a model-agnostic multi-agent harness and runtime layer for production AI workloads, organizing specialized agents into 'colonies' led by a persistent Queen agent. It provides state management, failure recovery, observability, and human-in-the-loop oversight, with MCP tool support and support for OpenAI, Anthropic, and Gemini models.

## Use cases
- orchestrate multiple ai agents to run a business process
- run autonomous agents in production with failure recovery
- add human approval steps to agent workflows
- build self-improving agent systems with mcp tools
- coordinate worker agents under a lead agent
- self-host an agent runtime for claude and openai models

## When to choose
- you need production-grade agent orchestration with state management and observability
- you want multi-agent collaboration with human-in-the-loop oversight
- you need a model-agnostic runtime supporting OpenAI, Anthropic, and Gemini
- you want MCP tool integration in an agent framework

## When to avoid
- you only need a simple single-agent chatbot
- you want a fully managed cloud service rather than self-hosting
- your use case is unrelated to LLM-driven agents

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, mcp, chatbot, monitoring
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted, cross-platform
- tags: multi-agent, human-in-the-loop, self-improving, model-agnostic, agent-colony, harness, production-ai, openai, anthropic, gemini, ai-agents, automation

## Member repositories
- aden-hive/hive (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.926107+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:17:15.957166+00:00, confidence not recorded.
  - readme: https://github.com/aden-hive/hive (fetched 2026-08-28T04:10:44.926107+00:00, sha 92a3c8afc6de)
- Data as of 2026-08-30T08:39:29.467469+00:00.