ClawForce: Let Claude Spawn People to Do Things at Scale

See how to use AI agents to commission real people for physical tasks, like ordering lunch or taking photos, bridging the digital and physical worlds.

claudecode MCP DoorDash Tasks Uber Direct

Overview

I built a lite MCP that let’s you expose commissioning real people to do anything in the physical world from an AI agentic workflow.

Think Terraform, but instead of provisioning servers, you’re provisioning people with Door Dash, Uber Direct, TaskRabbit, etc.

Links

https://github.com/mikeangstadt/clawforce
ClawForce is a TypeScript-based orchestration engine that enables AI agents to deploy human labor for physical tasks via an MCP server or REST API. Built on Node.js and SQLite, the system integrates gig-economy providers like DoorDash, Uber, and TaskRabbit to automate large-scale campaigns such as property inspections, retail audits, and personal errands. It features a CLI for managing concurrency-controlled dispatches, cross-provider cost estimation, and automated result aggregation.

Tech stack

claudecode

Claude Code is a command-line interface agent that executes complex engineering tasks by directly interacting with your local file system and git state.

Claude Code operates as a research-hardened agent within your terminal to automate high-to-low level development workflows. It handles codebase exploration, bug fixes, and test execution by issuing shell commands and editing files directly. Built on the Claude 3.5 Sonnet model, it manages multi-step refactors and git operations (commits, diffs, and merges) while maintaining context of your specific directory structure. Developers use it to bypass manual boilerplate and accelerate feature delivery through a secure, CLI-native interface.

https://docs.anthropic.com/en/docs/agents-and-tools/claude-code

View projects
MCP

MCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.

The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .

https://modelcontextprotocol.io/

View projects
DoorDash Tasks
Uber Direct

Finding related talks...