youtu-agent

Source#

• Repository: TencentCloudADP/youtu-agent
• Last source update: 2026-04-04
• Last verified: 2026-04-05

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: youtu-agent-repo-derived-worker
name: youtu-agent Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/youtu-agent/
source_repository: https://github.com/TencentCloudADP/youtu-agent
repository_default_branch: main
repository_language: Python
repository_license: NOASSERTION
repository_updated_at: 2026-04-04
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-04-05
tags:
  - agent-framework
  - agents
  - openai-agents
  - python
---

# youtu-agent Repo-Derived Worker

## Repo-derived summary
- Registry summary: A simple yet powerful agent framework that delivers with open-source models
- Repository description: A simple yet powerful agent framework that delivers with open-source models
- Stars (snapshot): 4,497
- Primary language: Python
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/TencentCloudADP/youtu-agent
- https://github.com/TencentCloudADP/youtu-agent/blob/main/README.md
- https://tencentcloudadp.github.io/youtu-agent/howto/skills/
- https://github.com/TencentCloudADP/youtu-agent/tree/rl/agl
- https://tencentcloudadp.github.io/youtu-agent/practice/

## Evidence notes (from repository text)
- README summary paragraph: # Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
- # Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
- - **Flexible architecture**: Built on https://github.com/openai/openai-agents-python, with extensible support for diverse model APIs (from `DeepSeek` to `gpt-oss`), tool integrations, and framework implementations.
- - 📢 [2025-11-03] New examples: we add the [**PPT generation**](examples/ppt_gen/README.md) and [**RAG**](configs/agents/examples/rag.yaml) examples.
- - 🛠️ [2025-09-28] Agent auto-generation now ships with companion tooling: describe a capability once and let `Youtu-Agent` build the tool for you. https://tencentcloudadp.github.io/youtu-agent/auto_generation/].
- - 📺 [2025-09-09] We hosted a live sharing the design philosophy and basic usage of `Youtu-Agent`. https://www.bilibili.com/video/BV1mypqz4EvS] https://doc.weixin.qq.com/doc/w3_AcMATAZtAPICNLgt3CbnxRWaYWnW4].

## Installation hints found in README
- `pip install utu_agent_ui-0.2.0-py3-none-any.whl`
- `uv pip install utu_agent_ui-0.2.0-py3-none-any.whl`

## 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: youtu-agent-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/youtu-agent/

Source URL: https://github.com/TencentCloudADP/youtu-agent