AI Worker worker.md

LLMTornado

The .NET library to build AI agents with 30+ built-in connectors.

Tool registry 590 stars C# MIT Worker-compatible

Source#

  • Repository: lofcz/LLMTornado
  • Last source update: 2026-04-02
  • Last verified: 2026-04-05

Tags#

a2aagentagent-frameworkagent-orchestrationagent2agentagentic-ai

Integration notes#

Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.

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: llmtornado-repo-derived-worker
name: LLMTornado Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/llmtornado/
source_repository: https://github.com/lofcz/LLMTornado
repository_default_branch: master
repository_language: C#
repository_license: MIT
repository_updated_at: 2026-04-02
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.9
derived_on: 2026-04-05
tags:
  - a2a
  - agent
  - agent-framework
  - agent-orchestration
  - agent2agent
  - agentic-ai
---

# LLMTornado Repo-Derived Worker

## Repo-derived summary
- Registry summary: The .NET library to build AI agents with 30+ built-in connectors.
- Repository description: The .NET library to build AI agents with 30+ built-in connectors.
- Stars (snapshot): 590
- Primary language: C#
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/lofcz/LLMTornado
- https://github.com/lofcz/LLMTornado/blob/master/README.md
- https://llmtornado.ai
- https://shields.io/nuget/v/LlmTornado?v=302&icon=nuget&label=LlmTornado
- https://shields.io/nuget/v/LlmTornado.Agents?v=303&icon=nuget&label=LlmTornado.Agents

## Evidence notes (from repository text)
- README summary paragraph: **Build AI agents and workflows in minutes with one toolkit and built-in connectors to 30+ API Providers & Vector Databases.**
- **Build AI agents and workflows in minutes with one toolkit and built-in connectors to 30+ API Providers & Vector Databases.**
- - 25/06 - https://llmtornado.ai/agents/tornado-agent/tools/function-tools system is added, freeing applications from authoring JSON schema manually. https://llmtornado.ai/mpc/mpc protocol is implemented.
- - 25/05 - https://llmtornado.ai/agents/tornado-agent/tools/response-tools system is added, allowing usage of `/responses` exclusive models from `/chat` endpoint.
- - 25/03 - https://llmtornado.ai/llmtornado/assistants/basics are implemented.
- dotnet add package LlmTornado.Agents # Agentic framework, higher-level abstractions

## Installation hints found in README
- No explicit package installation command detected in README text.

## 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: llmtornado-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/llmtornado/

Source URL: https://github.com/lofcz/LLMTornado