How to use Poirot: what you can do with it

4 use cases

• Run a deep research session from the terminal

  Install Poirot locally and ask it a research question in the full-screen TUI.

  • REPO HezaoHezao/poirot
  • Research
  • Intermediate
  View prompt

  Using the Poirot repo at <path to poirot checkout>, create a virtual environment, install it, set DEEPSEEK_API_KEY in .env, and launch `poirot` with the research question <research question>. Expected output: a research answer shown in the TUI conversation view. Verify that the status bar shows live token usage.

  Share Email me this

• Study the agent kernel and run its test suite

  Install the dev dependencies, run the tests, and trace the middleware layers.

  • REPO HezaoHezao/poirot
  • Research
  • Intermediate
  View prompt

  In the Poirot repo at <path to poirot checkout>, install the dev extras, run the test suite, and report the pass and fail counts. Expected output: a short summary of the test result and a list of the middleware named in the README. Verify that the README's claimed test count of 2400+ roughly matches the number of tests collected.

  Share Email me this

• Turn on long-term memory and skill evolution for a recurring topic

  Set the advanced feature flags so Poirot remembers past findings and improves its skills.

  • REPO HezaoHezao/poirot
  • Research
  • Intermediate
  View prompt

  In the Poirot repo at <path to poirot checkout>, add the memory and skill variables from the README's Enable Advanced Features block to .env, then run `poirot` on the topic <topic>. Expected output: a session where memory recall and skill injection are active. Verify that the variables are set in .env before launching.

  Share Email me this

• Run research tasks inside a Docker sandbox on Windows

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

  • REPO HezaoHezao/poirot
  • Research
  • Advanced
  View prompt

  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.

  Share Email me this

Quick start with Poirot

1. Check you have what it needs: Python 3.12 or newer; A DeepSeek API key (the README says to set DEEPSEEK_API_KEY in .env); Git and a terminal.
2. Open HezaoHezao/poirot on GitHub and read the README and license.
3. Clone the repo from https://github.com/HezaoHezao/poirot and change into the project folder. (inferred, check the README)
4. Create a virtual environment with python -m venv .venv.
5. Activate it with source .venv/bin/activate on Linux or macOS, or .venv\Scripts\activate on Windows.
6. Install the project with pip install -e ".[dev]".

These steps come from our top use case, Run a deep research session from the terminal, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for HezaoHezao/poirot

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

Poirot alternatives · Best AI repos for Research

About this repo

• Who it is forDevelopers and AI agent builders who want to run, study, or extend a research agent whose architecture is documented in the repo.
• Why it is hot255 stars, launched 90 days ago
• LanguagePython
• Sourcegithub.com/HezaoHezao/poirot · Back to Hot repos

Requirements

• 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

Related repos

• #8 this week REPO K-Dense-AI/scientific-agent-skills Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier REPO NVIDIA/personaplex PersonaPlex PersonaPlex is NVIDIA's real-time, full-duplex speech-to-speech conversational model based on Moshi that controls persona through text role prompts and audio voice conditioning.
• Trended earlier REPO VectifyAI/PageIndex PageIndex PageIndex is a vectorless, reasoning-based RAG system that builds a tree index of long documents and lets an LLM search it like a human reader, with local and cloud SDK modes.