OpenRath

Source#

• Repository: Rath-Team/OpenRath
• Last source update: 2026-07-10
• Last verified: 2026-07-12

Tags#

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: openrath-repo-derived-worker
name: OpenRath Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/openrath/
source_repository: https://github.com/Rath-Team/OpenRath
repository_default_branch: main
repository_language: Python
repository_license: BSD-3-Clause
repository_updated_at: 2026-07-10
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-07-12
tags:
  - agent-framework
  - agentic-ai
  - ai-agents
  - anthropic
  - lllm-agent
  - llm
---

# OpenRath Repo-Derived Worker

## Repo-derived summary
- Registry summary: An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
- Repository description: An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
- Stars (snapshot): 1,084
- Primary language: Python
- Worker mode classification: agent-orchestration-worker

## Extracted from
- https://github.com/Rath-Team/OpenRath
- https://github.com/Rath-Team/OpenRath/blob/main/README.md
- https://docs.openrath.com
- https://github.com/Rath-Team/OpenRath/issues

## Evidence notes (from repository text)
- README summary paragraph: **OpenRath is a PyTorch-like multi-agent & multi-session framework.**
- **OpenRath is a PyTorch-like multi-agent & multi-session framework.**
- It turns agent runtime state into explicit, composable Python objects:
- - **Session** carries conversation state and inter-agent collaboration lineage.
- - **Sandbox** decides where tools actually run.
- - **Memory** persists agent memory state across runs.

## Installation hints found in README
- `pip install openrath`
- `pip install "openrath[opensandbox]"`
- `pip install "openrath[openviking]"`

## 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: openrath-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/openrath/

Source URL: https://github.com/Rath-Team/OpenRath