Supports long-horizon autonomous task checkpointing and resumption for Expedia consumer travel agentic commerce workflows, including pause/resume and recovery for booking or itinerary tasks.
Supports long-horizon autonomous task checkpointing and resumption for Mastercard Agent Connect commerce workflows, including event-sourced state persistence and human-in-the-loop recovery.
Supports long-horizon autonomous task checkpointing and resumption for consumer agentic commerce workflows involving Meta Muse, including state persistence and fail-safe recovery.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@genpark-long-horizon-autonomous-task-resumption-skill checkpoint my current task, then resume it from the last saved state"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🌐 GenPark MCP Hub • 📦 GenPark Official • 📖 Documentation
genpark-long-horizon-autonomous-task-resumption-skill delivers robust, industrial-grade capabilities engineered for Consumer Agentic Commerce (e.g. Meta Muse, Expedia, Mastercard Agent Connect) and Enterprise Workplace Execution (e.g. Tencent WorkBuddy Goal-to-PPT/Excel deliverable workflows). Built exclusively on the Python standard library with zero external runtime dependencies, it integrates seamlessly as a native Model Context Protocol (MCP) server or an importable Python module.
Long-Horizon Autonomous Task Checkpoint & Resumption Engine (inspired by Persistent Consumer & Enterprise Agents). Provides cryptographic event-sourcing state persistence, idempotency key deduplication, scheduled timeout heartbeats, human-in-the-loop pause-and-resume tokens, and fail-safe recovery.
Zero-Dependency Architecture: Runs anywhere Python 3.9+ is installed without pip install overhead or supply-chain vulnerabilities.
Model Context Protocol (MCP) First: Compatible with Claude Desktop, Cursor, GenPark Engine, Meta Muse, and enterprise managed agent runtimes.
Deterministic & Safe: Rigorous state machine models, cryptographic ledger hashes, mathematical dependency graphs, and full telemetry.
High Concurrency & Low Latency: In-memory caching, topological cycle detection, and optimized execution loops.
Related MCP server: CONTINUUM
from client import LongHorizonAutonomousTaskResumptionEngine
client = LongHorizonAutonomousTaskResumptionEngine()
result = client.create_task_session()
print(result)Run the MCP server via standard JSON-RPC 2.0 stdio:
python mcp_server.pyVerify standard compliance and self-tests:
python mcp_server.py --testAdd this tool to your claude_desktop_config.json or Cursor MCP settings:
{
"mcpServers": {
"genpark-long-horizon-autonomous-task-resumption-skill": {
"command": "python",
"args": ["/absolute/path/to/genpark-long-horizon-autonomous-task-resumption-skill/mcp_server.py"]
}
}
}Run the included verification suite:
python example_usage.pyThis project is licensed under the MIT License - see the LICENSE file for details.
Developed with ❤️ by the GenPark Autonomous Agent Ecosystem Team.
This server cannot be deployed
Agent checkpoints. Resume after context resets and handoffs with retry-safe, versioned saves.
Durable background job execution, async task scheduling, and state persistence for AI agents.
Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.