agents-universe

Source#

• Repository: agents-universe/agents-universe
• Last source update: 2026-10-25
• Last verified: 2026-10-25

Tags#

Integration notes#

Framework-level abstraction; derive bounded worker contracts from concrete tasks and APIs in docs/examples.

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: agents-universe-repo-derived-worker
name: agents-universe Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/agents-universe/
source_repository: https://github.com/agents-universe/agents-universe
repository_default_branch: main
repository_language: Python
repository_license: Apache-2.0
repository_updated_at: 2026-10-25
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-10-25
tags:
  - agent
  - agent-framework
  - agent-orchestration
  - agent-skill
  - agentic-ai
  - ai-agents
---

# agents-universe Repo-Derived Worker

## Repo-derived summary
- Registry summary: 不是问答机器人，而是能真正干活的数字分身。共享智能体，共享项目上下文，让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中
- Repository description: 不是问答机器人，而是能真正干活的数字分身。共享智能体，共享项目上下文，让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中
- Stars (snapshot): 729
- Primary language: Python
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/agents-universe/agents-universe
- https://github.com/agents-universe/agents-universe/blob/main/README.md
- https://github.com/agents-universe/agents-universe/actions/workflows/ci.yml/badge.svg
- https://img.shields.io/website?url=https%3A%2F%2Fagents-universe.com&label=agents-universe.com&color=7c3aed
- https://agents-universe.com

## Evidence notes (from repository text)
- README summary paragraph: Agents Universe 是一个开源（Apache-2.0）的企业级 AI Agent 平台。它不是又一个"更聪明的聊天框"，而是要让智能体真正成为能干活的人：入职读懂文档、接任务先规划、以个人身份与权限执行、留下可审计的轨迹，并把这一切沉淀为每个人都能复用、共同建设的资产。
- https://github.com/agents-universe/agents-universe/actions/workflows/ci.yml/badge.svg](https://github.com/agents-universe/agents-universe/actions/workflows/ci.yml)
- Agents Universe 是一个开源（Apache-2.0）的企业级 AI Agent 平台。它不是又一个"更聪明的聊天框"，而是要让智能体真正成为能干活的人：入职读懂文档、接任务先规划、以个人身份与权限执行、留下可审计的轨迹，并把这一切沉淀为每个人都能复用、共同建设的资产。
- ![Agents Universe 系统界面](docs/images/system_screenshot.webp)
- - **是什么** — 开源企业级 AI Agent 平台：多 LLM 统一接入、10 个开箱即用的智能体、Docker 一键自托管。详见[核心特性](#核心特性)
- - **解决什么** — 智能体的两极困局：开发者框架门槛高、经验不可传承；低代码平台没有身份、权限与可审计轨迹。详见[为什么是 Agents Universe](#为什么是-agents-universe)

## Installation hints found in README
- `pip install -e ../agent-core -e .`
- `pip install`、`find -delete` 等`

## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.

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

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

### 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: agents-universe-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/agents-universe/

Source URL: https://github.com/agents-universe/agents-universe