DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run research tasks inside a Docker sandbox on Windows with Poirot

Route Poirot's tool execution through a Docker sandbox with WSL2 and enable specialist delegation.

Short answer: Set up the project with pip install -e ".[dev]" after creating a virtual environment, as in the Quick Start; then Confirm that Docker is running under WSL2 on the Windows machine; add POIROT_SANDBOX_USE=Poirot.backend.agents.sandbox.docker.docker_sandbox_provider:DockerSandboxProvider and POIROT_SANDBOX_EXECUTOR=wsl to .env. All steps.

  • Research
  • Advanced
  • 60 minutes
  • From the README
  • Any agent

Credentials. Each specialist CLI (pi, codex, or claude) runs as its own process with its own LLM, so keep each provider's key in that tool's config and out of shared files.

Who it is forA developer on Windows with WSL2 who wants agent-run code and file writes isolated from the host.

The problemLetting an agent run commands and write files directly on a host machine exposes that machine to unintended changes.

The outcomeA Poirot session where file writes and shell commands run in a Docker sandbox and outputs persist in the mount area.

What you need first

  • Python 3.12 or newer
  • A DeepSeek API key (the README says to set DEEPSEEK_API_KEY in .env)
  • Git and a terminal
  • Docker only if you want the container sandbox

Steps

  1. Set up the project with pip install -e ".[dev]" after creating a virtual environment, as in the Quick Start.
  2. Confirm that Docker is running under WSL2 on the Windows machine. (inferred, check the README)
  3. Add POIROT_SANDBOX_USE=Poirot.backend.agents.sandbox.docker.docker_sandbox_provider:DockerSandboxProvider and POIROT_SANDBOX_EXECUTOR=wsl to .env.
  4. Add POIROT_MULTIAGENT_ENABLED=true to .env to allow specialist delegation.
  5. Start Poirot with poirot, then save outputs under /mnt/poirot/user-data/ so they persist.

Prompt for your agent

In the Poirot repo at <path to poirot checkout>, set the Docker sandbox and WSL executor variables in .env, then run `poirot` with the task <task>. Expected output: a completed task with its output files written under /mnt/poirot/user-data/. Verify that the output file exists in the mount path after the run.

Caveat. The README says DockerPathGuard only allows writes under /mnt/poirot/user-data/, so files saved elsewhere inside the container may be lost when the container exits.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for HezaoHezao/poirot and "Run research tasks inside a Docker sandbox on Windows"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer