AI Worker worker.md

hive

Multi-Agent Harness for Production AI

Automation platform 10,355 stars Python Apache-2.0 Worker-compatible

Source#

  • Repository: aden-hive/hive
  • Last source update: 2026-05-17
  • Last verified: 2026-05-17

Tags#

agentagent-frameworkagent-skillsanthropicautomationautonomous-agents

Integration notes#

Repository is workflow-oriented; map each workflow step to explicit worker contracts for predictability.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: hive-repo-derived-worker
name: hive Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/hive/
source_repository: https://github.com/aden-hive/hive
repository_default_branch: main
repository_language: Python
repository_license: Apache-2.0
repository_updated_at: 2026-05-17
worker_mode: workflow-automation-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-05-17
tags:
  - agent
  - agent-framework
  - agent-skills
  - anthropic
  - automation
  - autonomous-agents
---

# hive Repo-Derived Worker

## Repo-derived summary
- Registry summary: Multi-Agent Harness for Production AI
- Repository description: Multi-Agent Harness for Production AI
- Stars (snapshot): 10,355
- Primary language: Python
- Worker mode classification: workflow-automation-worker

## Extracted from
- https://github.com/aden-hive/hive
- https://github.com/aden-hive/hive/blob/main/README.md
- http://honeycomb.open-hive.com/
- https://docs.adenhq.com/
- https://docs.adenhq.com/getting-started/quickstart

## Evidence notes (from repository text)
- README summary paragraph: English | 简体中文 | Español | हिन्दी | Português | 日本語 | Русский | 한국어
- The agent harness for production workloads — state management, failure recovery, observability, and human oversight so your agents actually run.
- - ✅ Multi-Agent Coordination for parallel task execution
- - ✅ Role-based memory that evolves with your projects
- Hive is the multi-agent harness layer for teams moving AI agents from prototype to production. Single agents like Openclaw and Cowork can finish personal jobs pretty well but lack the rigor to fulfil business processes.
- - Want AI agents that **execute real business processes**, not demos

## Installation hints found in README
- `pip install`.`
- `pip install -e .` from the repository root will create a placeholder package and Hive will not function correctly.`

## worker.md contract (derived starter)
Purpose: Execute one automation workflow step in a bounded worker run.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "trigger",
    "step"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "trigger": {
      "type": "object"
    },
    "step": {
      "type": "string"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "run_id",
    "step",
    "status",
    "artifacts"
  ],
  "properties": {
    "run_id": {
      "type": "string"
    },
    "step": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "artifacts": {
      "type": "array"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

  • Save this as a worker spec file (for example: hive-my-task.worker.md).
  • Replace the input/output schemas and purpose with your real bounded task.
  • Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/hive/

Source URL: https://github.com/aden-hive/hive